Header logo is


2010


no image
Graph Kernels

Vishwanathan, SVN., Schraudolph, NN., Kondor, R., Borgwardt, KM.

Journal of Machine Learning Research, 11, pages: 1201-1242, April 2010 (article)

Abstract
We present a unified framework to study graph kernels, special cases of which include the random walk (G{\"a}rtner et al., 2003; Borgwardt et al., 2005) and marginalized (Kashima et al., 2003, 2004; Mahét al., 2004) graph kernels. Through reduction to a Sylvester equation we improve the time complexity of kernel computation between unlabeled graphs with n vertices from O(n6) to O(n3). We find a spectral decomposition approach even more efficient when computing entire kernel matrices. For labeled graphs we develop conjugate gradient and fixed-point methods that take O(dn3) time per iteration, where d is the size of the label set. By extending the necessary linear algebra to Reproducing Kernel Hilbert Spaces (RKHS) we obtain the same result for d-dimensional edge kernels, and O(n4) in the infinite-dimensional case; on sparse graphs these algorithms only take O(n2) time per iteration in all cases. Experiments on graphs from bioinformatics and other application domains show that these techniques can speed up computation of the kernel by an order of magnitude or more. We also show that certain rational kernels (Cortes et al., 2002, 2003, 2004) when specialized to graphs reduce to our random walk graph kernel. Finally, we relate our framework to R-convolution kernels (Haussler, 1999) and provide a kernel that is close to the optimal assignment kernel of kernel of Fr{\"o}hlich et al. (2006) yet provably positive semi-definite.

ei

PDF Web [BibTex]

2010


PDF Web [BibTex]


no image
Gene function prediction from synthetic lethality networks via ranking on demand

Lippert, C., Ghahramani, Z., Borgwardt, KM.

Bioinformatics, 26(7):912-918, April 2010 (article)

Abstract
Motivation: Synthetic lethal interactions represent pairs of genes whose individual mutations are not lethal, while the double mutation of both genes does incur lethality. Several studies have shown a correlation between functional similarity of genes and their distances in networks based on synthetic lethal interactions. However, there is a lack of algorithms for predicting gene function from synthetic lethality interaction networks. Results: In this article, we present a novel technique called kernelROD for gene function prediction from synthetic lethal interaction networks based on kernel machines. We apply our novel algorithm to Gene Ontology functional annotation prediction in yeast. Our experiments show that our method leads to improved gene function prediction compared with state-of-the-art competitors and that combining genetic and congruence networks leads to a further improvement in prediction accuracy.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
A toolbox for predicting G-quadruplex formation and stability

Wong, HM., Stegle, O., Rodgers, S., Huppert, J.

Journal of Nucleic Acids, 2010(564946):1-6, March 2010 (article)

Abstract
G-quadruplexes are four stranded nucleic acid structures formed around a core of guanines, arranged in squares with mutual hydrogen bonding. Many of these structures are highly thermally stable, especially in the presence of monovalent cations, such as those found under physiological conditions. Understanding of their physiological roles is expanding rapidly, and they have been implicated in regulating gene transcription and translation among other functions. We have built a community-focused website to act as a repository for the information that is now being developed. At its core, this site has a detailed database (QuadDB) of predicted G-quadruplexes in the human and other genomes, together with the predictive algorithm used to identify them. We also provide a QuadPredict server, which predicts thermal stability and acts as a repository for experimental data from all researchers. There are also a number of other data sources with computational predictions. We anticipate that the wide availability of this information will be of use both to researchers already active in this exciting field and to those who wish to investigate a particular gene hypothesis.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
A Novel Protocol for Accuracy Assessment in Classification of Very High Resolution Images

Persello, C., Bruzzone, L.

IEEE Transactions on Geoscience and Remote Sensing, 48(3):1232-1244, March 2010 (article)

Abstract
This paper presents a novel protocol for the accuracy assessment of the thematic maps obtained by the classification of very high resolution images. As the thematic accuracy alone is not sufficient to adequately characterize the geometrical properties of high-resolution classification maps, we propose a protocol that is based on the analysis of two families of indices: 1) the traditional thematic accuracy indices and 2) a set of novel geometric indices that model different geometric properties of the objects recognized in the map. In this context, we present a set of indices that characterize five different types of geometric errors in the classification map: 1) oversegmentation; 2) undersegmentation; 3) edge location; 4) shape distortion; and 5) fragmentation. Moreover, we propose a new approach for tuning the free parameters of supervised classifiers on the basis of a multiobjective criterion function that aims at selecting the parameter values that result in the classification map that jointly optimize thematic and geometric error indices. Experimental results obtained on QuickBird images show the effectiveness of the proposed protocol in selecting classification maps characterized by a better tradeoff between thematic and geometric accuracies than standard procedures based only on thematic accuracy measures. In addition, results obtained with support vector machine classifiers confirm the effectiveness of the proposed multiobjective technique for the selection of free-parameter values for the classification algorithm.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
On the Entropy Production of Time Series with Unidirectional Linearity

Janzing, D.

Journal of Statistical Physics, 138(4-5):767-779, March 2010 (article)

Abstract
There are non-Gaussian time series that admit a causal linear autoregressive moving average (ARMA) model when regressing the future on the past, but not when regressing the past on the future. The reason is that, in the latter case, the regression residuals are not statistically independent of the regressor. In previous work, we have experimentally verified that many empirical time series indeed show such a time inversion asymmetry. For various physical systems, it is known that time-inversion asymmetries are linked to the thermodynamic entropy production in non-equilibrium states. Here we argue that unidirectional linearity is also accompanied by entropy generation. To this end, we study the dynamical evolution of a physical toy system with linear coupling to an infinite environment and show that the linearity of the dynamics is inherited by the forward-time conditional probabilities, but not by the backward-time conditionals. The reason is that the environment permanently provides particles that are in a product state before they interact with the system, but show statistical dependence afterwards. From a coarse-grained perspective, the interaction thus generates entropy. We quantitatively relate the strength of the non-linearity of the backward process to the minimal amount of entropy generation. The paper thus shows that unidirectional linearity is an indirect implication of the thermodynamic arrow of time, given that the joint dynamics of the system and its environment is linear.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning

Morimura, T., Uchibe, E., Yoshimoto, J., Peters, J., Doya, K.

Neural Computation, 22(2):342-376, February 2010 (article)

Abstract
Most conventional policy gradient reinforcement learning (PGRL) algorithms neglect (or do not explicitly make use of) a term in the average reward gradient with respect to the policy parameter. That term involves the derivative of the stationary state distribution that corresponds to the sensitivity of its distribution to changes in the policy parameter. Although the bias introduced by this omission can be reduced by setting the forgetting rate γ for the value functions close to 1, these algorithms do not permit γ to be set exactly at γ = 1. In this article, we propose a method for estimating the log stationary state distribution derivative (LSD) as a useful form of the derivative of the stationary state distribution through backward Markov chain formulation and a temporal difference learning framework. A new policy gradient (PG) framework with an LSD is also proposed, in which the average reward gradient can be estimated by setting //!-- MFG_und--//amp;#947; = 0, so it becomes unnecessary to learn the value functions. We also test the performance of the proposed algorithms using simple benchmark tasks and show that these can improve the performances of existing PG methods.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Bayesian Online Multitask Learning of Gaussian Processes

Pillonetto, G., Dinuzzo, F., De Nicolao, G.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(2):193-205, February 2010 (article)

Abstract
Standard single-task kernel methods have recently been extended to the case of multitask learning in the context of regularization theory. There are experimental results, especially in biomedicine, showing the benefit of the multitask approach compared to the single-task one. However, a possible drawback is computational complexity. For instance, when regularization networks are used, complexity scales as the cube of the overall number of training data, which may be large when several tasks are involved. The aim of this paper is to derive an efficient computational scheme for an important class of multitask kernels. More precisely, a quadratic loss is assumed and each task consists of the sum of a common term and a task-specific one. Within a Bayesian setting, a recursive online algorithm is obtained, which updates both estimates and confidence intervals as new data become available. The algorithm is tested on two simulated problems and a real data set relative to xenobiotics administration in human patients.

ei

DOI [BibTex]

DOI [BibTex]


no image
The semigroup approach to transport processes in networks

Dorn, B., Fijavz, M., Nagel, R., Radl, A.

Physica D: Nonlinear Phenomena, 239(15):1416-1421, January 2010 (article)

Abstract
We explain how operator semigroups can be used to study transport processes in networks. This method is applied to a linear Boltzmann equation on a finite as well as on an infinite network and yields well-posedness and information on the long term behavior of the solutions to the presented problems.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Optimization of k-Space Trajectories for Compressed Sensing by Bayesian Experimental Design

Seeger, M., Nickisch, H., Pohmann, R., Schölkopf, B.

Magnetic Resonance in Medicine, 63(1):116-126, January 2010 (article)

Abstract
The optimization of k-space sampling for nonlinear sparse MRI reconstruction is phrased as a Bayesian experimental design problem. Bayesian inference is approximated by a novel relaxation to standard signal processing primitives, resulting in an efficient optimization algorithm for Cartesian and spiral trajectories. On clinical resolution brain image data from a Siemens 3T scanner, automatically optimized trajectories lead to significantly improved images, compared to standard low-pass, equispaced, or variable density randomized designs. Insights into the nonlinear design optimization problem for MRI are given.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Consistent Nonparametric Tests of Independence

Gretton, A., Györfi, L.

Journal of Machine Learning Research, 11, pages: 1391-1423, 2010 (article)

ei

PDF [BibTex]

PDF [BibTex]


no image
Inferring latent task structure for Multitask Learning by Multiple Kernel Learning

Widmer, C., Toussaint, N., Altun, Y., Rätsch, G.

BMC Bioinformatics, 11 Suppl 8, pages: S5, 2010 (article)

Abstract
The lack of sufficient training data is the limiting factor for many Machine Learning applications in Computational Biology. If data is available for several different but related problem domains, Multitask Learning algorithms can be used to learn a model based on all available information. In Bioinformatics, many problems can be cast into the Multitask Learning scenario by incorporating data from several organisms. However, combining information from several tasks requires careful consideration of the degree of similarity between tasks. Our proposed method simultaneously learns or refines the similarity between tasks along with the Multitask Learning classifier. This is done by formulating the Multitask Learning problem as Multiple Kernel Learning, using the recently published q-Norm MKL algorithm.

ei

Web DOI [BibTex]

Web DOI [BibTex]

2003


no image
Concentration Inequalities for Sub-Additive Functions Using the Entropy Method

Bousquet, O.

Stochastic Inequalities and Applications, 56, pages: 213-247, Progress in Probability, (Editors: Giné, E., C. Houdré and D. Nualart), November 2003 (article)

Abstract
We obtain exponential concentration inequalities for sub-additive functions of independent random variables under weak conditions on the increments of those functions, like the existence of exponential moments for these increments. As a consequence of these general inequalities, we obtain refinements of Talagrand's inequality for empirical processes and new bounds for randomized empirical processes. These results are obtained by further developing the entropy method introduced by Ledoux.

ei

PostScript [BibTex]

2003


PostScript [BibTex]


no image
Statistical Learning Theory, Capacity and Complexity

Schölkopf, B.

Complexity, 8(4):87-94, July 2003 (article)

Abstract
We give an exposition of the ideas of statistical learning theory, followed by a discussion of how a reinterpretation of the insights of learning theory could potentially also benefit our understanding of a certain notion of complexity.

ei

Web DOI [BibTex]


no image
Dealing with large Diagonals in Kernel Matrices

Weston, J., Schölkopf, B., Eskin, E., Leslie, C., Noble, W.

Annals of the Institute of Statistical Mathematics, 55(2):391-408, June 2003 (article)

Abstract
In kernel methods, all the information about the training data is contained in the Gram matrix. If this matrix has large diagonal values, which arises for many types of kernels, then kernel methods do not perform well: We propose and test several methods for dealing with this problem by reducing the dynamic range of the matrix while preserving the positive definiteness of the Hessian of the quadratic programming problem that one has to solve when training a Support Vector Machine, which is a common kernel approach for pattern recognition.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
The em Algorithm for Kernel Matrix Completion with Auxiliary Data

Tsuda, K., Akaho, S., Asai, K.

Journal of Machine Learning Research, 4, pages: 67-81, May 2003 (article)

ei

PDF [BibTex]

PDF [BibTex]


no image
Constructing Descriptive and Discriminative Non-linear Features: Rayleigh Coefficients in Kernel Feature Spaces

Mika, S., Rätsch, G., Weston, J., Schölkopf, B., Smola, A., Müller, K.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(5):623-628, May 2003 (article)

Abstract
We incorporate prior knowledge to construct nonlinear algorithms for invariant feature extraction and discrimination. Employing a unified framework in terms of a nonlinearized variant of the Rayleigh coefficient, we propose nonlinear generalizations of Fisher‘s discriminant and oriented PCA using support vector kernel functions. Extensive simulations show the utility of our approach.

ei

DOI [BibTex]

DOI [BibTex]


no image
Tractable Inference for Probabilistic Data Models

Csato, L., Opper, M., Winther, O.

Complexity, 8(4):64-68, April 2003 (article)

Abstract
We present an approximation technique for probabilistic data models with a large number of hidden variables, based on ideas from statistical physics. We give examples for two nontrivial applications. © 2003 Wiley Periodicals, Inc.

ei

PDF GZIP Web [BibTex]

PDF GZIP Web [BibTex]


no image
Feature selection and transduction for prediction of molecular bioactivity for drug design

Weston, J., Perez-Cruz, F., Bousquet, O., Chapelle, O., Elisseeff, A., Schölkopf, B.

Bioinformatics, 19(6):764-771, April 2003 (article)

Abstract
Motivation: In drug discovery a key task is to identify characteristics that separate active (binding) compounds from inactive (non-binding) ones. An automated prediction system can help reduce resources necessary to carry out this task. Results: Two methods for prediction of molecular bioactivity for drug design are introduced and shown to perform well in a data set previously studied as part of the KDD (Knowledge Discovery and Data Mining) Cup 2001. The data is characterized by very few positive examples, a very large number of features (describing three-dimensional properties of the molecules) and rather different distributions between training and test data. Two techniques are introduced specifically to tackle these problems: a feature selection method for unbalanced data and a classifier which adapts to the distribution of the the unlabeled test data (a so-called transductive method). We show both techniques improve identification performance and in conjunction provide an improvement over using only one of the techniques. Our results suggest the importance of taking into account the characteristics in this data which may also be relevant in other problems of a similar type.

ei

Web [BibTex]


no image
Use of the Zero-Norm with Linear Models and Kernel Methods

Weston, J., Elisseeff, A., Schölkopf, B., Tipping, M.

Journal of Machine Learning Research, 3, pages: 1439-1461, March 2003 (article)

Abstract
We explore the use of the so-called zero-norm of the parameters of linear models in learning. Minimization of such a quantity has many uses in a machine learning context: for variable or feature selection, minimizing training error and ensuring sparsity in solutions. We derive a simple but practical method for achieving these goals and discuss its relationship to existing techniques of minimizing the zero-norm. The method boils down to implementing a simple modification of vanilla SVM, namely via an iterative multiplicative rescaling of the training data. Applications we investigate which aid our discussion include variable and feature selection on biological microarray data, and multicategory classification.

ei

PDF PostScript PDF [BibTex]

PDF PostScript PDF [BibTex]


no image
An Introduction to Variable and Feature Selection.

Guyon, I., Elisseeff, A.

Journal of Machine Learning, 3, pages: 1157-1182, 2003 (article)

ei

[BibTex]

[BibTex]


no image
New Approaches to Statistical Learning Theory

Bousquet, O.

Annals of the Institute of Statistical Mathematics, 55(2):371-389, 2003 (article)

Abstract
We present new tools from probability theory that can be applied to the analysis of learning algorithms. These tools allow to derive new bounds on the generalization performance of learning algorithms and to propose alternative measures of the complexity of the learning task, which in turn can be used to derive new learning algorithms.

ei

PostScript [BibTex]

PostScript [BibTex]

1998


no image
SVMs — a practical consequence of learning theory

Schölkopf, B.

IEEE Intelligent Systems and their Applications, 13(4):18-21, July 1998 (article)

Abstract
My first exposure to Support Vector Machines came this spring when heard Sue Dumais present impressive results on text categorization using this analysis technique. This issue's collection of essays should help familiarize our readers with this interesting new racehorse in the Machine Learning stable. Bernhard Scholkopf, in an introductory overview, points out that a particular advantage of SVMs over other learning algorithms is that it can be analyzed theoretically using concepts from computational learning theory, and at the same time can achieve good performance when applied to real problems. Examples of these real-world applications are provided by Sue Dumais, who describes the aforementioned text-categorization problem, yielding the best results to date on the Reuters collection, and Edgar Osuna, who presents strong results on application to face detection. Our fourth author, John Platt, gives us a practical guide and a new technique for implementing the algorithm efficiently.

ei

PDF Web DOI [BibTex]

1998


PDF Web DOI [BibTex]


no image
Learning view graphs for robot navigation

Franz, M., Schölkopf, B., Mallot, H., Bülthoff, H.

Autonomous Robots, 5(1):111-125, March 1998 (article)

Abstract
We present a purely vision-based scheme for learning a topological representation of an open environment. The system represents selected places by local views of the surrounding scene, and finds traversable paths between them. The set of recorded views and their connections are combined into a graph model of the environment. To navigate between views connected in the graph, we employ a homing strategy inspired by findings of insect ethology. In robot experiments, we demonstrate that complex visual exploration and navigation tasks can thus be performed without using metric information.

ei

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]