Header logo is


2014


no image
IM3SHAPE: Maximum likelihood galaxy shear measurement code for cosmic gravitational lensing

Zuntz, J., Kacprzak, T., Voigt, L., Hirsch, M., Rowe, B., Bridle, S.

Astrophysics Source Code Library, 1, pages: 09013, 2014 (article)

ei

link (url) [BibTex]

2014


link (url) [BibTex]


no image
Causal Discovery in the Presence of Time-Dependent Relations or Small Sample Size

Huang, B.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Event-Based State Estimation With Variance-Based Triggering

Trimpe, S., D’Andrea, R.

IEEE Transactions on Automatic Control, 59(12):3266-3281, 2014 (article)

am ics

PDF Supplementary material DOI Project Page [BibTex]

PDF Supplementary material DOI Project Page [BibTex]


no image
Efficient nearest neighbors via robust sparse hashing

Cherian, A., Sra, S., Morellas, V., Papanikolopoulos, N.

IEEE Transactions on Image Processing, 23(8):3646-3655, 2014 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Efficient Structured Matrix Rank Minimization

Yu, A. W., Ma, W., Yu, Y., Carbonell, J., Sra, S.

Advances in Neural Information Processing Systems 27, pages: 1350-1358, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), Curran Associates, Inc., 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Towards building a Crowd-Sourced Sky Map

Lang, D., Hogg, D., Schölkopf, B.

In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, JMLR W\&CP 33, pages: 549–557, (Editors: S. Kaski and J. Corander), JMLR.org, AISTATS, 2014 (inproceedings)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Incremental Local Gaussian Regression

Meier, F., Hennig, P., Schaal, S.

In Advances in Neural Information Processing Systems 27, pages: 972-980, (Editors: Z. Ghahramani, M. Welling, C. Cortes, N.D. Lawrence and K.Q. Weinberger), 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014, clmc (inproceedings)

am ei pn

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Sérsic galaxy models in weak lensing shape measurement: model bias, noise bias and their interaction

Kacprzak, T., Bridle, S., Rowe, B., Voigt, L., Zuntz, J., Hirsch, M., MacCrann, N.

Monthly Notices of the Royal Astronomical Society, 441(3):2528-2538, Oxford University Press, 2014 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Learning to Deblur

Schuler, C. J., Hirsch, M., Harmeling, S., Schölkopf, B.

In NIPS 2014 Deep Learning and Representation Learning Workshop, 28th Annual Conference on Neural Information Processing Systems (NIPS), 2014 (inproceedings)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Analysis of Distance Functions in Graphs

Alamgir, M.

University of Hamburg, Germany, University of Hamburg, Germany, 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Efficient Bayesian Local Model Learning for Control

Meier, F., Hennig, P., Schaal, S.

In Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pages: 2244 - 2249, IROS, 2014, clmc (inproceedings)

Abstract
Model-based control is essential for compliant controland force control in many modern complex robots, like humanoidor disaster robots. Due to many unknown and hard tomodel nonlinearities, analytical models of such robots are oftenonly very rough approximations. However, modern optimizationcontrollers frequently depend on reasonably accurate models,and degrade greatly in robustness and performance if modelerrors are too large. For a long time, machine learning hasbeen expected to provide automatic empirical model synthesis,yet so far, research has only generated feasibility studies butno learning algorithms that run reliably on complex robots.In this paper, we combine two promising worlds of regressiontechniques to generate a more powerful regression learningsystem. On the one hand, locally weighted regression techniquesare computationally efficient, but hard to tune due to avariety of data dependent meta-parameters. On the other hand,Bayesian regression has rather automatic and robust methods toset learning parameters, but becomes quickly computationallyinfeasible for big and high-dimensional data sets. By reducingthe complexity of Bayesian regression in the spirit of local modellearning through variational approximations, we arrive at anovel algorithm that is computationally efficient and easy toinitialize for robust learning. Evaluations on several datasetsdemonstrate very good learning performance and the potentialfor a general regression learning tool for robotics.

am ei pn

PDF link (url) DOI [BibTex]

PDF link (url) DOI [BibTex]


no image
Perspective: Intelligent Systems: Bits and Bots

Spatz, J. P., Schaal, S.

Nature, (509), 2014, clmc (article)

Abstract
What is intelligence, and can we create it? Animals can perceive, reason, react and learn, but they are just one example of an intelligent system. Intelligent systems could be robots as large as humans, helping with search-and- rescue operations in dangerous places, or smart devices as tiny as a cell, delivering drugs to a target within the body. Even computing systems can be intelligent, by perceiving the world, crawling the web and processing â??big dataâ?? to extract and learn from complex information.Understanding not only how intelligence can be reproduced, but also how to build systems that put these ideas into practice, will be a challenge. Small intelligent systems will require new materials and fabrication methods, as well as com- pact information processors and power sources. And for nano-sized systems, the rules change altogether. The laws of physics operate very differently at tiny scales: for a nanorobot, swimming through water is like struggling through treacle.Researchers at the Max Planck Institute for Intelligent Systems have begun to solve these problems by developing new computational methods, experiment- ing with unique robotic systems and fabricating tiny, artificial propellers, like bacterial flagella, to propel nanocreations through their environment.

am

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Stability Analysis of Distributed Event-Based State Estimation

Trimpe, S.

In Proceedings of the 53rd IEEE Conference on Decision and Control, Los Angeles, CA, 2014 (inproceedings)

Abstract
An approach for distributed and event-based state estimation that was proposed in previous work [1] is analyzed and extended to practical networked systems in this paper. Multiple sensor-actuator-agents observe a dynamic process, sporadically exchange their measurements over a broadcast network according to an event-based protocol, and estimate the process state from the received data. The event-based approach was shown in [1] to mimic a centralized Luenberger observer up to guaranteed bounds, under the assumption of identical estimates on all agents. This assumption, however, is unrealistic (it is violated by a single packet drop or slight numerical inaccuracy) and removed herein. By means of a simulation example, it is shown that non-identical estimates can actually destabilize the overall system. To achieve stability, the event-based communication scheme is supplemented by periodic (but infrequent) exchange of the agentsâ?? estimates and reset to their joint average. When the local estimates are used for feedback control, the stability guarantee for the estimation problem extends to the event-based control system.

am ics

PDF Supplementary material DOI Project Page [BibTex]

PDF Supplementary material DOI Project Page [BibTex]


no image
Towards an optimal stochastic alternating direction method of multipliers

Azadi, S., Sra, S.

Proceedings of the 31st International Conference on Machine Learning, 32, pages: 620-628, (Editors: Xing, E. P. and Jebara, T.), JMLR, ICML, 2014 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Diminished White Matter Integrity in Patients with Systemic Lupus Erythematosus

Schmidt-Wilcke, T., Cagnoli, P., Wang, P., Schultz, T., Lotz, A., Mccune, W. J., Sundgren, P. C.

NeuroImage: Clinical, 5, pages: 291-297, 2014 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Open Problem: Finding Good Cascade Sampling Processes for the Network Inference Problem

Gomez Rodriguez, M., Song, L., Schölkopf, B.

Proceedings of the 27th Conference on Learning Theory, 35, pages: 1276-1279, (Editors: Balcan, M.-F. and Szepesvári, C.), JMLR.org, COLT, 2014 (conference)

ei

PDF [BibTex]

PDF [BibTex]


no image
Data-driven autonomous manipulation

Pastor, P.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Dual Execution of Optimized Contact Interaction Trajectories

Toussaint, M., Ratliff, N., Bohg, J., Righetti, L., Englert, P., Schaal, S.

In 2014 IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 47-54, IEEE, Chicago, USA, 2014 (inproceedings)

Abstract
Efficient manipulation requires contact to reduce uncertainty. The manipulation literature refers to this as funneling: a methodology for increasing reliability and robustness by leveraging haptic feedback and control of environmental interaction. However, there is a fundamental gap between traditional approaches to trajectory optimization and this concept of robustness by funneling: traditional trajectory optimizers do not discover force feedback strategies. From a POMDP perspective, these behaviors could be regarded as explicit observation actions planned to sufficiently reduce uncertainty thereby enabling a task. While we are sympathetic to the full POMDP view, solving full continuous-space POMDPs in high-dimensions is hard. In this paper, we propose an alternative approach in which trajectory optimization objectives are augmented with new terms that reward uncertainty reduction through contacts, explicitly promoting funneling. This augmentation shifts the responsibility of robustness toward the actual execution of the optimized trajectories. Directly tracing trajectories through configuration space would lose all robustness-dual execution achieves robustness by devising force controllers to reproduce the temporal interaction profile encoded in the dual solution of the optimization problem. This work introduces dual execution in depth and analyze its performance through robustness experiments in both simulation and on a real-world robotic platform.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Information-Theoretic Bounded Rationality and ϵ-Optimality

Braun, DA, Ortega, PA

Entropy, 16(8):4662-4676, August 2014 (article)

Abstract
Bounded rationality concerns the study of decision makers with limited information processing resources. Previously, the free energy difference functional has been suggested to model bounded rational decision making, as it provides a natural trade-off between an energy or utility function that is to be optimized and information processing costs that are measured by entropic search costs. The main question of this article is how the information-theoretic free energy model relates to simple \(\epsilon\)-optimality models of bounded rational decision making, where the decision maker is satisfied with any action in an \(\epsilon\)-neighborhood of the optimal utility. We find that the stochastic policies that optimize the free energy trade-off comply with the notion of \(\epsilon\)-optimality. Moreover, this optimality criterion even holds when the environment is adversarial. We conclude that the study of bounded rationality based on \(\epsilon\)-optimality criteria that abstract away from the particulars of the information processing constraints is compatible with the information-theoretic free energy model of bounded rationality.

ei

DOI [BibTex]

DOI [BibTex]


no image
An autonomous manipulation system based on force control and optimization

Righetti, L., Kalakrishnan, M., Pastor, P., Binney, J., Kelly, J., Voorhies, R. C., Sukhatme, G. S., Schaal, S.

Autonomous Robots, 36(1-2):11-30, January 2014 (article)

Abstract
In this paper we present an architecture for autonomous manipulation. Our approach is based on the belief that contact interactions during manipulation should be exploited to improve dexterity and that optimizing motion plans is useful to create more robust and repeatable manipulation behaviors. We therefore propose an architecture where state of the art force/torque control and optimization-based motion planning are the core components of the system. We give a detailed description of the modules that constitute the complete system and discuss the challenges inherent to creating such a system. We present experimental results for several grasping and manipulation tasks to demonstrate the performance and robustness of our approach.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Occam’s Razor in sensorimotor learning

Genewein, T, Braun, D

Proceedings of the Royal Society of London B, 281(1783):1-7, May 2014 (article)

Abstract
A large number of recent studies suggest that the sensorimotor system uses probabilistic models to predict its environment and makes inferences about unobserved variables in line with Bayesian statistics. One of the important features of Bayesian statistics is Occam's Razor—an inbuilt preference for simpler models when comparing competing models that explain some observed data equally well. Here, we test directly for Occam's Razor in sensorimotor control. We designed a sensorimotor task in which participants had to draw lines through clouds of noisy samples of an unobserved curve generated by one of two possible probabilistic models—a simple model with a large length scale, leading to smooth curves, and a complex model with a short length scale, leading to more wiggly curves. In training trials, participants were informed about the model that generated the stimulus so that they could learn the statistics of each model. In probe trials, participants were then exposed to ambiguous stimuli. In probe trials where the ambiguous stimulus could be fitted equally well by both models, we found that participants showed a clear preference for the simpler model. Moreover, we found that participants’ choice behaviour was quantitatively consistent with Bayesian Occam's Razor. We also show that participants’ drawn trajectories were similar to samples from the Bayesian predictive distribution over trajectories and significantly different from two non-probabilistic heuristics. In two control experiments, we show that the preference of the simpler model cannot be simply explained by a difference in physical effort or by a preference for curve smoothness. Our results suggest that Occam's Razor is a general behavioural principle already present during sensorimotor processing.

ei

DOI [BibTex]

DOI [BibTex]


no image
Generalized Thompson sampling for sequential decision-making and causal inference

Ortega, PA, Braun, DA

Complex Adaptive Systems Modeling, 2(2):1-23, March 2014 (article)

Abstract
Purpose Sampling an action according to the probability that the action is believed to be the optimal one is sometimes called Thompson sampling. Methods Although mostly applied to bandit problems, Thompson sampling can also be used to solve sequential adaptive control problems, when the optimal policy is known for each possible environment. The predictive distribution over actions can then be constructed by a Bayesian superposition of the policies weighted by their posterior probability of being optimal. Results Here we discuss two important features of this approach. First, we show in how far such generalized Thompson sampling can be regarded as an optimal strategy under limited information processing capabilities that constrain the sampling complexity of the decision-making process. Second, we show how such Thompson sampling can be extended to solve causal inference problems when interacting with an environment in a sequential fashion. Conclusion In summary, our results suggest that Thompson sampling might not merely be a useful heuristic, but a principled method to address problems of adaptive sequential decision-making and causal inference.

ei

DOI [BibTex]

DOI [BibTex]


no image
Learning and Exploration in a Novel Dimensionality-Reduction Task

Ebert, J, Kim, S, Schweighofer, N., Sternad, D, Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2009), Amsterdam, Netherlands, 2014 (inproceedings)

am

[BibTex]

[BibTex]


no image
Learning of grasp selection based on shape-templates

Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T., Schaal, S.

Autonomous Robots, 36(1-2):51-65, January 2014 (article)

Abstract
The ability to grasp unknown objects still remains an unsolved problem in the robotics community. One of the challenges is to choose an appropriate grasp configuration, i.e., the 6D pose of the hand relative to the object and its finger configuration. In this paper, we introduce an algorithm that is based on the assumption that similarly shaped objects can be grasped in a similar way. It is able to synthesize good grasp poses for unknown objects by finding the best matching object shape templates associated with previously demonstrated grasps. The grasp selection algorithm is able to improve over time by using the information of previous grasp attempts to adapt the ranking of the templates to new situations. We tested our approach on two different platforms, the Willow Garage PR2 and the Barrett WAM robot, which have very different hand kinematics. Furthermore, we compared our algorithm with other grasp planners and demonstrated its superior performance. The results presented in this paper show that the algorithm is able to find good grasp configurations for a large set of unknown objects from a relatively small set of demonstrations, and does improve its performance over time.

am mg

link (url) DOI [BibTex]


no image
Balancing experiments on a torque-controlled humanoid with hierarchical inverse dynamics

Herzog, A., Righetti, L., Grimminger, F., Pastor, P., Schaal, S.

In 2014 IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 981-988, IEEE, Chicago, USA, 2014 (inproceedings)

Abstract
Recently several hierarchical inverse dynamics controllers based on cascades of quadratic programs have been proposed for application on torque controlled robots. They have important theoretical benefits but have never been implemented on a torque controlled robot where model inaccuracies and real-time computation requirements can be problematic. In this contribution we present an experimental evaluation of these algorithms in the context of balance control for a humanoid robot. The presented experiments demonstrate the applicability of the approach under real robot conditions (i.e. model uncertainty, estimation errors, etc). We propose a simplification of the optimization problem that allows us to decrease computation time enough to implement it in a fast torque control loop. We implement a momentum-based balance controller which shows robust performance in face of unknown disturbances, even when the robot is standing on only one foot. In a second experiment, a tracking task is evaluated to demonstrate the performance of the controller with more complicated hierarchies. Our results show that hierarchical inverse dynamics controllers can be used for feedback control of humanoid robots and that momentum-based balance control can be efficiently implemented on a real robot.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Full Dynamics LQR Control of a Humanoid Robot: An Experimental Study on Balancing and Squatting

Mason, S., Righetti, L., Schaal, S.

In 2014 IEEE-RAS International Conference on Humanoid Robots, pages: 374-379, IEEE, Madrid, Spain, 2014 (inproceedings)

Abstract
Humanoid robots operating in human environments require whole-body controllers that can offer precise tracking and well-defined disturbance rejection behavior. In this contribution, we propose an experimental evaluation of a linear quadratic regulator (LQR) using a linearization of the full robot dynamics together with the contact constraints. The advantage of the controller is that it explicitly takes into account the coupling between the different joints to create optimal feedback controllers for whole-body control. We also propose a method to explicitly regulate other tasks of interest, such as the regulation of the center of mass of the robot or its angular momentum. In order to evaluate the performance of linear optimal control designs in a real-world scenario (model uncertainty, sensor noise, imperfect state estimation, etc), we test the controllers in a variety of tracking and balancing experiments on a torque controlled humanoid (e.g. balancing, split plane balancing, squatting, pushes while squatting, and balancing on a wheeled platform). The proposed control framework shows a reliable push recovery behavior competitive with more sophisticated balance controllers, rejecting impulses up to 11.7 Ns with peak forces of 650 N, with the added advantage of great computational simplicity. Furthermore, the controller is able to track squatting trajectories up to 1 Hz without relinearization, suggesting that the linearized dynamics is sufficient for significant ranges of motion.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Assessing randomness and complexity in human motion trajectories through analysis of symbolic sequences

Peng, Z, Genewein, T, Braun, DA

Frontiers in Human Neuroscience, 8(168):1-13, March 2014 (article)

Abstract
Complexity is a hallmark of intelligent behavior consisting both of regular patterns and random variation. To quantitatively assess the complexity and randomness of human motion, we designed a motor task in which we translated subjects' motion trajectories into strings of symbol sequences. In the first part of the experiment participants were asked to perform self-paced movements to create repetitive patterns, copy pre-specified letter sequences, and generate random movements. To investigate whether the degree of randomness can be manipulated, in the second part of the experiment participants were asked to perform unpredictable movements in the context of a pursuit game, where they received feedback from an online Bayesian predictor guessing their next move. We analyzed symbol sequences representing subjects' motion trajectories with five common complexity measures: predictability, compressibility, approximate entropy, Lempel-Ziv complexity, as well as effective measure complexity. We found that subjects’ self-created patterns were the most complex, followed by drawing movements of letters and self-paced random motion. We also found that participants could change the randomness of their behavior depending on context and feedback. Our results suggest that humans can adjust both complexity and regularity in different movement types and contexts and that this can be assessed with information-theoretic measures of the symbolic sequences generated from movement trajectories.

ei

DOI [BibTex]

DOI [BibTex]


no image
Curiosity-driven learning with Context Tree Weighting

Peng, Z, Braun, DA

pages: 366-367, IEEE, Piscataway, NJ, USA, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB), October 2014 (conference)

Abstract
In the first simulation, the intrinsic motivation of the agent was given by measuring learning progress through reduction in informational surprise (Figure 1 A-C). This way the agent should first learn the action that is easiest to learn (a1), and then switch to other actions that still allow for learning (a2) and ignore actions that cannot be learned at all (a3). This is exactly what we found in our simple environment. Compared to the original developmental learning algorithm based on learning progress proposed by Oudeyer [2], our Context Tree Weighting approach does not require local experts to do prediction, rather it learns the conditional probability distribution over observations given action in one structure. In the second simulation, the intrinsic motivation of the agent was given by measuring compression progress through improvement in compressibility (Figure 1 D-F). The agent behaves similarly: the agent first concentrates on the action with the most predictable consequence and then switches over to the regular action where the consequence is more difficult to predict, but still learnable. Unlike the previous simulation, random actions are also interesting to some extent because the compressed symbol strings use 8-bit representations, while only 2 bits are required for our observation space. Our preliminary results suggest that Context Tree Weighting might provide a useful representation to study problems of development.

ei

DOI [BibTex]

DOI [BibTex]


no image
State Estimation for a Humanoid Robot

Rotella, N., Bloesch, M., Righetti, L., Schaal, S.

In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 952-958, IEEE, Chicago, USA, 2014 (inproceedings)

Abstract
This paper introduces a framework for state estimation on a humanoid robot platform using only common proprioceptive sensors and knowledge of leg kinematics. The presented approach extends that detailed in prior work on a point-foot quadruped platform by adding the rotational constraints imposed by the humanoid's flat feet. As in previous work, the proposed Extended Kalman Filter accommodates contact switching and makes no assumptions about gait or terrain, making it applicable on any humanoid platform for use in any task. A nonlinear observability analysis is performed on both the point-foot and flat-foot filters and it is concluded that the addition of rotational constraints significantly simplifies singular cases and improves the observability characteristics of the system. Results on a simulated walking dataset demonstrate the performance gain of the flat-foot filter as well as confirm the results of the presented observability analysis.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Monte Carlo methods for exact & efficient solution of the generalized optimality equations

Ortega, PA, Braun, DA, Tishby, N

pages: 4322-4327, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), June 2014 (conference)

Abstract
Previous work has shown that classical sequential decision making rules, including expectimax and minimax, are limit cases of a more general class of bounded rational planning problems that trade off the value and the complexity of the solution, as measured by its information divergence from a given reference. This allows modeling a range of novel planning problems having varying degrees of control due to resource constraints, risk-sensitivity, trust and model uncertainty. However, so far it has been unclear in what sense information constraints relate to the complexity of planning. In this paper, we introduce Monte Carlo methods to solve the generalized optimality equations in an efficient \& exact way when the inverse temperatures in a generalized decision tree are of the same sign. These methods highlight a fundamental relation between inverse temperatures and the number of Monte Carlo proposals. In particular, it is seen that the number of proposals is essentially independent of the size of the decision tree.

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2011


no image
Statistical estimation for optimization problems on graphs

Langovoy, M., Sra, S.

In pages: 1-6, NIPS Workshop on Discrete Optimization in Machine Learning (DISCML): Uncertainty, Generalization and Feedback , December 2011 (inproceedings)

Abstract
Large graphs abound in machine learning, data mining, and several related areas. A useful step towards analyzing such graphs is that of obtaining certain summary statistics — e.g., or the expected length of a shortest path between two nodes, or the expected weight of a minimum spanning tree of the graph, etc. These statistics provide insight into the structure of a graph, and they can help predict global properties of a graph. Motivated thus, we propose to study statistical properties of structured subgraphs (of a given graph), in particular, to estimate the expected objective function value of a combinatorial optimization problem over these subgraphs. The general task is very difficult, if not unsolvable; so for concreteness we describe a more specific statistical estimation problem based on spanning trees. We hope that our position paper encourages others to also study other types of graphical structures for which one can prove nontrivial statistical estimates.

ei

PDF Web [BibTex]

2011


PDF Web [BibTex]


no image
Projected Newton-type methods in machine learning

Schmidt, M., Kim, D., Sra, S.

In Optimization for Machine Learning, pages: 305-330, (Editors: Sra, S., Nowozin, S. and Wright, S. J.), MIT Press, Cambridge, MA, USA, December 2011 (inbook)

Abstract
We consider projected Newton-type methods for solving large-scale optimization problems arising in machine learning and related fields. We first introduce an algorithmic framework for projected Newton-type methods by reviewing a canonical projected (quasi-)Newton method. This method, while conceptually pleasing, has a high computation cost per iteration. Thus, we discuss two variants that are more scalable, namely, two-metric projection and inexact projection methods. Finally, we show how to apply the Newton-type framework to handle non-smooth objectives. Examples are provided throughout the chapter to illustrate machine learning applications of our framework.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
On the discardability of data in Support Vector Classification problems

Del Favero, S., Varagnolo, D., Dinuzzo, F., Schenato, L., Pillonetto, G.

In pages: 3210-3215, IEEE, Piscataway, NJ, USA, 50th IEEE Conference on Decision and Control and European Control Conference (CDC - ECC), December 2011 (inproceedings)

Abstract
We analyze the problem of data sets reduction for support vector classification. The work is also motivated by distributed problems, where sensors collect binary measurements at different locations moving inside an environment that needs to be divided into a collection of regions labeled in two different ways. The scope is to let each agent retain and exchange only those measurements that are mostly informative for the collective reconstruction of the decision boundary. For the case of separable classes, we provide the exact conditions and an efficient algorithm to determine if an element in the training set can become a support vector when new data arrive. The analysis is then extended to the non-separable case deriving a sufficient discardability condition and a general data selection scheme for classification. Numerical experiments relative to the distributed problem show that the proposed procedure allows the agents to exchange a small amount of the collected data to obtain a highly predictive decision boundary.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Combined whole-body PET/MR imaging: MR contrast agents do not affect the quantitative accuracy of PET following attenuation correction

Lois, C., Kupferschläger, J., Bezrukov, I., Schmidt, H., Werner, M., Mannheim, J., Pichler, B., Schwenzer, N., Beyer, T.

(SST15-05 ), 97th Scientific Assemble and Annual Meeting of the Radiological Society of North America (RSNA), December 2011 (talk)

Abstract
PURPOSE Combined PET/MR imaging entails the use of MR contrast agents (MRCA) as part of integrated protocols. We assess additional attenuation of the PET emission signals in the presence of oral and intraveneous (iv) MRCA made up of iron oxide and Gd-chelates, respectively. METHOD AND MATERIALS Phantom scans were performed on a clinical PET/CT (Biograph HiRez16, Siemens) and integrated whole-body PET/MR (Biograph mMR, Siemens) using oral (Lumirem) and intraveneous (Gadovist) MRCA. Reference PET attenuation values were determined on a small-animal PET (Inveon, Siemens) using standard PET transmission imaging (TX). Seven syringes of 5mL were filled with (a) Water, (b) Lumirem_100 (100% conc.), (c) Gadovist_100 (100%), (d) Gadovist_18 (18%), (e) Gadovist_02 (0.2%), (f) Imeron-400 CT iv-contrast (100%) and (g) Imeron-400 (2.4%). The same set of syringes was scanned on CT (Sensation16, Siemens) at 120kVp and 160mAs. The effect of MRCA on the attenuation of PET emission data was evaluated using a 20cm cylinder filled uniformly with [18F]-FDG (FDG) in water (BGD). Three 4.5cm diameter cylinders were inserted into the phantom: (C1) Teflon, (C2) Water+FDG (2:1) and (C3) Lumirem_100+FDG (2:1). Two 50mL syringes filled with Gadovist_02+FDG (Sy1) and water+FDG (Sy2) were attached to the sides of (C1) to mimick the effects of iv-contrast in vessels near bone. Syringe-to-background activity ratio was 4-to-1. PET emission data were acquired for 10min each using the PET/CT and the PET/MR. Images were reconstructed using CT- and MR-based attenuation correction. RESULTS Mean linear PET attenuation (cm-1) on TX was (a) 0.098, (b) 0.098, (c) 0.300, (d) 0.134, (e) 0.095, (f) 0.397 and (g) 0.105. Corresponding CT attenuation (HU) was: (a) 5, (b) 14, (c) 3070, (d) 1040, (e) 13, (f) 3070 and (g) 347. Lumirem had little effect on PET attenuation with (C3) being 13% and 10% higher than (C2) on PET/CT and PET/MR, respectively. Gadovist_02 had even smaller effects with (Sy1) being 2.5% lower than (Sy2) on PET/CT and 1.2% higher than (Sy2) on PET/MR. CONCLUSION MRCA in high and clinically relevant concentrations have attenuation values similar to that of CT contrast and water, respectively. In clinical PET/MR scenarios MRCA are not expected to lead to significant attenuation of the PET emission signals.

ei

Web [BibTex]

Web [BibTex]


no image
Causal Inference on Discrete Data using Additive Noise Models

Peters, J., Janzing, D., Schölkopf, B.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2436-2450, December 2011 (article)

Abstract
Inferring the causal structure of a set of random variables from a finite sample of the joint distribution is an important problem in science. The case of two random variables is particularly challenging since no (conditional) independences can be exploited. Recent methods that are based on additive noise models suggest the following principle: Whenever the joint distribution {\bf P}^{(X,Y)} admits such a model in one direction, e.g., Y=f(X)+N, N \perp\kern-6pt \perp X, but does not admit the reversed model X=g(Y)+\tilde{N}, \tilde{N} \perp\kern-6pt \perp Y, one infers the former direction to be causal (i.e., X\rightarrow Y). Up to now, these approaches only dealt with continuous variables. In many situations, however, the variables of interest are discrete or even have only finitely many states. In this work, we extend the notion of additive noise models to these cases. We prove that it almost never occurs that additive noise models can be fit in both directions. We further propose an efficient algorithm that is able to perform this way of causal inference on finite samples of discrete variables. We show that the algorithm works on both synthetic and real data sets.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Spontaneous epigenetic variation in the Arabidopsis thaliana methylome

Becker, C., Hagmann, J., Müller, J., Koenig, D., Stegle, O., Borgwardt, K., Weigel, D.

Nature, 480(7376):245-249, December 2011 (article)

Abstract
Heritable epigenetic polymorphisms, such as differential cytosine methylation, can underlie phenotypic variation1, 2. Moreover, wild strains of the plant Arabidopsis thaliana differ in many epialleles3, 4, and these can influence the expression of nearby genes1, 2. However, to understand their role in evolution5, it is imperative to ascertain the emergence rate and stability of epialleles, including those that are not due to structural variation. We have compared genome-wide DNA methylation among 10 A. thaliana lines, derived 30 generations ago from a common ancestor6. Epimutations at individual positions were easily detected, and close to 30,000 cytosines in each strain were differentially methylated. In contrast, larger regions of contiguous methylation were much more stable, and the frequency of changes was in the same low range as that of DNA mutations7. Like individual positions, the same regions were often affected by differential methylation in independent lines, with evidence for recurrent cycles of forward and reverse mutations. Transposable elements and short interfering RNAs have been causally linked to DNA methylation8. In agreement, differentially methylated sites were farther from transposable elements and showed less association with short interfering RNA expression than invariant positions. The biased distribution and frequent reversion of epimutations have important implications for the potential contribution of sequence-independent epialleles to plant evolution.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Information, learning and falsification

Balduzzi, D.

In pages: 1-4, NIPS Philosophy and Machine Learning Workshop, December 2011 (inproceedings)

Abstract
There are (at least) three approaches to quantifying information. The first, algorithmic information or Kolmogorov complexity, takes events as strings and, given a universal Turing machine, quantifies the information content of a string as the length of the shortest program producing it [1]. The second, Shannon information, takes events as belonging to ensembles and quantifies the information resulting from observing the given event in terms of the number of alternate events that have been ruled out [2]. The third, statistical learning theory, has introduced measures of capacity that control (in part) the expected risk of classifiers [3]. These capacities quantify the expectations regarding future data that learning algorithms embed into classifiers. Solomonoff and Hutter have applied algorithmic information to prove remarkable results on universal induction. Shannon information provides the mathematical foundation for communication and coding theory. However, both approaches have shortcomings. Algorithmic information is not computable, severely limiting its practical usefulness. Shannon information refers to ensembles rather than actual events: it makes no sense to compute the Shannon information of a single string – or rather, there are many answers to this question depending on how a related ensemble is constructed. Although there are asymptotic results linking algorithmic and Shannon information, it is unsatisfying that there is such a large gap – a difference in kind – between the two measures. This note describes a new method of quantifying information, effective information, that links algorithmic information to Shannon information, and also links both to capacities arising in statistical learning theory [4, 5]. After introducing the measure, we show that it provides a non-universal analog of Kolmogorov complexity. We then apply it to derive basic capacities in statistical learning theory: empirical VC-entropy and empirical Rademacher complexity. A nice byproduct of our approach is an interpretation of the explanatory power of a learning algorithm in terms of the number of hypotheses it falsifies [6], counted in two different ways for the two capacities. We also discuss how effective information relates to information gain, Shannon and mutual information.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Optimization for Machine Learning

Sra, S., Nowozin, S., Wright, S.

pages: 494, Neural information processing series, MIT Press, Cambridge, MA, USA, December 2011 (book)

Abstract
The interplay between optimization and machine learning is one of the most important developments in modern computational science. Optimization formulations and methods are proving to be vital in designing algorithms to extract essential knowledge from huge volumes of data. Machine learning, however, is not simply a consumer of optimization technology but a rapidly evolving field that is itself generating new optimization ideas. This book captures the state of the art of the interaction between optimization and machine learning in a way that is accessible to researchers in both fields. Optimization approaches have enjoyed prominence in machine learning because of their wide applicability and attractive theoretical properties. The increasing complexity, size, and variety of today's machine learning models call for the reassessment of existing assumptions. This book starts the process of reassessment. It describes the resurgence in novel contexts of established frameworks such as first-order methods, stochastic approximations, convex relaxations, interior-point methods, and proximal methods. It also devotes attention to newer themes such as regularized optimization, robust optimization, gradient and subgradient methods, splitting techniques, and second-order methods. Many of these techniques draw inspiration from other fields, including operations research, theoretical computer science, and subfields of optimization. The book will enrich the ongoing cross-fertilization between the machine learning community and these other fields, and within the broader optimization community.

ei

Web [BibTex]

Web [BibTex]


no image
A general linear non-Gaussian state-space model: Identifiability, identification, and applications

Zhang, K., Hyvärinen, A.

In JMLR Workshop and Conference Proceedings Volume 20, pages: 113-128, (Editors: Hsu, C.-N. , W.S. Lee ), MIT Press, Cambridge, MA, USA, 3rd Asian Conference on Machine Learning (ACML), November 2011 (inproceedings)

Abstract
State-space modeling provides a powerful tool for system identification and prediction. In linear state-space models the data are usually assumed to be Gaussian and the models have certain structural constraints such that they are identifiable. In this paper we propose a non-Gaussian state-space model which does not have such constraints. We prove that this model is fully identifiable. We then propose an efficient two-step method for parameter estimation: one first extracts the subspace of the latent processes based on the temporal information of the data, and then performs multichannel blind deconvolution, making use of both the temporal information and non-Gaussianity. We conduct a series of simulations to illustrate the performance of the proposed method. Finally, we apply the proposed model and parameter estimation method on real data, including major world stock indices and magnetoencephalography (MEG) recordings. Experimental results are encouraging and show the practical usefulness of the proposed model and method.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Non-stationary correction of optical aberrations

Schuler, C., Hirsch, M., Harmeling, S., Schölkopf, B.

In pages: 659-666 , (Editors: DN Metaxas and L Quan and A Sanfeliu and LJ Van Gool), IEEE, Piscataway, NJ, USA, 13th IEEE International Conference on Computer Vision (ICCV), November 2011 (inproceedings)

Abstract
Taking a sharp photo at several megapixel resolution traditionally relies on high grade lenses. In this paper, we present an approach to alleviate image degradations caused by imperfect optics. We rely on a calibration step to encode the optical aberrations in a space-variant point spread function and obtain a corrected image by non-stationary deconvolution. By including the Bayer array in our image formation model, we can perform demosaicing as part of the deconvolution.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Learning low-rank output kernels

Dinuzzo, F., Fukumizu, K.

In JMLR Workshop and Conference Proceedings Volume 20, pages: 181-196, (Editors: Hsu, C.-N. , W.S. Lee), JMLR, Cambridge, MA, USA, 3rd Asian Conference on Machine Learning (ACML) , November 2011 (inproceedings)

Abstract
Output kernel learning techniques allow to simultaneously learn a vector-valued function and a positive semidefinite matrix which describes the relationships between the outputs. In this paper, we introduce a new formulation that imposes a low-rank constraint on the output kernel and operates directly on a factor of the kernel matrix. First, we investigate the connection between output kernel learning and a regularization problem for an architecture with two layers. Then, we show that a variety of methods such as nuclear norm regularized regression, reduced-rank regression, principal component analysis, and low rank matrix approximation can be seen as special cases of the output kernel learning framework. Finally, we introduce a block coordinate descent strategy for learning low-rank output kernels.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
HHfrag: HMM-based fragment detection using HHpred

Kalev, I., Habeck, M.

Bioinformatics, 27(22):3110-3116, November 2011 (article)

Abstract
Motivation: Over the last decade, both static and dynamic fragment libraries for protein structure prediction have been introduced. The former are built from clusters in either sequence or structure space and aim to extract a universal structural alphabet. The latter are tailored for a particular query protein sequence and aim to provide local structural templates that need to be assembled in order to build the full-length structure. Results: Here, we introduce HHfrag, a dynamic HMM-based fragment search method built on the profile–profile comparison tool HHpred. We show that HHfrag provides advantages over existing fragment assignment methods in that it: (i) improves the precision of the fragments at the expense of a minor loss in sequence coverage; (ii) detects fragments of variable length (6–21 amino acid residues); (iii) allows for gapped fragments and (iv) does not assign fragments to regions where there is no clear sequence conservation. We illustrate the usefulness of fragments detected by HHfrag on targets from most recent CASP.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Spatiotemporal mapping of rhythmic activity in the inferior convexity of the macaque prefrontal cortex

Panagiotaropoulos, T., Besserve, M., Crocker, B., Kapoor, V., Tolias, A., Panzeri, S., Logothetis, N.

41(239.15), 41st Annual Meeting of the Society for Neuroscience (Neuroscience), November 2011 (poster)

Abstract
The inferior convexity of the macaque prefrontal cortex (icPFC) is known to be involved in higher order processing of sensory information mediating stimulus selection, attention and working memory. Until now, the vast majority of electrophysiological investigations of the icPFC employed single electrode recordings. As a result, relatively little is known about the spatiotemporal structure of neuronal activity in this cortical area. Here we study in detail the spatiotemporal properties of local field potentials (LFP's) in the icPFC using multi electrode recordings during anesthesia. We computed the LFP-LFP coherence as a function of frequency for thousands of pairs of simultaneously recorded sites anterior to the arcuate and inferior to the principal sulcus. We observed two distinct peaks of coherent oscillatory activity between approximately 4-10 and 15-25 Hz. We then quantified the instantaneous phase of these frequency bands using the Hilbert transform and found robust phase gradients across recording sites. The dependency of the phase on the spatial location reflects the existence of traveling waves of electrical activity in the icPFC. The dominant axis of these traveling waves roughly followed the ventral-dorsal plane. Preliminary results show that repeated visual stimulation with a 10s movie had no dramatic effect on the spatial structure of the traveling waves. Traveling waves of electrical activity in the icPFC could reflect highly organized cortical processing in this area of prefrontal cortex.

ei

Web [BibTex]

Web [BibTex]


no image
Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning

Hachiya, H., Peters, J., Sugiyama, M.

Neural Computation, 23(11):2798-2832, November 2011 (article)

Abstract
Direct policy search is a promising reinforcement learning framework, in particular for controlling continuous, high-dimensional systems. Policy search often requires a large number of samples for obtaining a stable policy update estimator, and this is prohibitive when the sampling cost is expensive. In this letter, we extend an expectation-maximization-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, reward-weighted regression with sample reuse (R), is demonstrated through robot learning experiments.

ei

Web DOI [BibTex]


no image
Stability Condition for Teleoperation System with Packet Loss

Hong, A., Cho, JH., Lee, DY.

In pages: 760-761, 2011 KSME Annual Fall Conference, November 2011 (inproceedings)

Abstract
This paper focuses on the stability condition of teleoperation system where there is a packet loss in communication channel. Communication channel between master and slave cause packet loss and it obviously leads to a performance degradation and instability of teleoperation system. We consider two-channel control architecture for teleoperation system, and control inputs to remote site are produced by position of master and slave. In this paper, teleoperation system is modeled in discrete domain to include packet loss process. Also, the stability condition for teleoperation system with packet loss is discussed with input-to-state stability. Finally, the stability condition is presented in LMI approach.

ei

[BibTex]

[BibTex]


no image
Model Learning in Robotics: a Survey

Nguyen-Tuong, D., Peters, J.

Cognitive Processing, 12(4):319-340, November 2011 (article)

Abstract
Models are among the most essential tools in robotics, such as kinematics and dynamics models of the robot's own body and controllable external objects. It is widely believed that intelligent mammals also rely on internal models in order to generate their actions. However, while classical robotics relies on manually generated models that are based on human insights into physics, future autonomous, cognitive robots need to be able to automatically generate models that are based on information which is extracted from the data streams accessible to the robot. In this paper, we survey the progress in model learning with a strong focus on robot control on a kinematic as well as dynamical level. Here, a model describes essential information about the behavior of the environment and the in uence of an agent on this environment. In the context of model based learning control, we view the model from three di fferent perspectives. First, we need to study the di erent possible model learning architectures for robotics. Second, we discuss what kind of problems these architecture and the domain of robotics imply for the applicable learning methods. From this discussion, we deduce future directions of real-time learning algorithms. Third, we show where these scenarios have been used successfully in several case studies.

ei

PDF [BibTex]

PDF [BibTex]


no image
Fast removal of non-uniform camera shake

Hirsch, M., Schuler, C., Harmeling, S., Schölkopf, B.

In pages: 463-470 , (Editors: DN Metaxas and L Quan and A Sanfeliu and LJ Van Gool), IEEE, Piscataway, NJ, USA, 13th IEEE International Conference on Computer Vision (ICCV), November 2011 (inproceedings)

Abstract
Camera shake leads to non-uniform image blurs. State-of-the-art methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this paper we develop a forward model based on the efficient filter flow framework, incorporating the particularities of camera shake, and show how an efficient algorithm for blur removal can be obtained. Comprehensive comparisons on a number of real-world blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Cooperative Cuts: a new use of submodularity in image segmentation

Jegelka, S.

Second I.S.T. Austria Symposium on Computer Vision and Machine Learning, October 2011 (talk)

ei

Web [BibTex]

Web [BibTex]


no image
Effect of MR Contrast Agents on Quantitative Accuracy of PET in Combined Whole-Body PET/MR Imaging

Lois, C., Bezrukov, I., Schmidt, H., Schwenzer, N., Werner, M., Pichler, B., Kupferschläger, J., Beyer, T.

2011(MIC3-3), 2011 IEEE Nuclear Science Symposium, Medical Imaging Conference (NSS-MIC), October 2011 (talk)

Abstract
Combined whole-body PET/MR systems are being tested in clinical practice today. Integrated imaging protocols entail the use of MR contrast agents (MRCA) that could bias PET attenuation correction. In this work, we assess the effect of MRCA in PET/MR imaging. We analyze the effect of oral and intravenous MRCA on PET activity after attenuation correction. We conclude that in clinical scenarios, MRCA are not expected to lead to significant attenuation of PET signals, and that attenuation maps are not biased after the ingestion of adequate oral contrasts.

ei

Web [BibTex]

Web [BibTex]