Header logo is


2015


no image
Quantifying changes in climate variability and extremes: Pitfalls and their overcoming

Sippel, S., Zscheischler, J., Heimann, M., Otto, F. E. L., Peters, J., Mahecha, M. D.

Geophysical Research Letters, 42(22):9990-9998, November 2015 (article)

ei

DOI [BibTex]

2015


DOI [BibTex]


no image
Diversity of sharp wave-ripple LFP signatures reveals differentiated brain-wide dynamical events

Ramirez-Villegas, J. F., Logothetis, N. K., Besserve, M.

Proceedings of the National Academy of Sciences U.S.A, 112(46):E6379-E6387, November 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Noise masking of White’s illusion exposes the weakness of current spatial filtering models of lightness perception

Betz, T., Shapley, R. M., Wichmann, F. A., Maertens, M.

Journal of Vision, 15(14):1-17, October 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Shifts of Gamma Phase across Primary Visual Cortical Sites Reflect Dynamic Stimulus-Modulated Information Transfer

Besserve, M., Lowe, S. C., Logothetis, N. K., Schölkopf, B., Panzeri, S.

PLOS Biology, 13(9):e1002257, September 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Semi-Supervised Interpolation in an Anticausal Learning Scenario

Janzing, D., Schölkopf, B.

Journal of Machine Learning Research, 16, pages: 1923-1948, September 2015 (article)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Testing the role of luminance edges in White’s illusion with contour adaptation

Betz, T., Shapley, R. M., Wichmann, F. A., Maertens, M.

Journal of Vision, 15(11):1-16, August 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Blind multirigid retrospective motion correction of MR images

Loktyushin, A., Nickisch, H., Pohmann, R., Schölkopf, B.

Magnetic Resonance in Medicine, 73(4):1457-1468, April 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
A quantum advantage for inferring causal structure

Ried, K., Agnew, M., Vermeyden, L., Janzing, D., Spekkens, R. W., Resch, K. J.

Nature Physics, 11(5):414-420, March 2015 (article)

Abstract
The problem of inferring causal relations from observed correlations is relevant to a wide variety of scientific disciplines. Yet given the correlations between just two classical variables, it is impossible to determine whether they arose from a causal influence of one on the other or a common cause influencing both. Only a randomized trial can settle the issue. Here we consider the problem of causal inference for quantum variables. We show that the analogue of a randomized trial, causal tomography, yields a complete solution. We also show that, in contrast to the classical case, one can sometimes infer the causal structure from observations alone. We implement a quantum-optical experiment wherein we control the causal relation between two optical modes, and two measurement schemes—with and without randomization—that extract this relation from the observed correlations. Our results show that entanglement and quantum coherence provide an advantage for causal inference.

ei

DOI [BibTex]

DOI [BibTex]


no image
Positive definite matrices and the S-divergence

Sra, S.

Proceedings of the American Mathematical Society, 2015, Published electronically: October 22, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Structural Intervention Distance (SID) for Evaluating Causal Graphs

Peters, J., Bühlmann, P.

Neural Computation , 27(3):771-799, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Likelihood and Consilience: On Forster’s Counterexamples to the Likelihood Theory of Evidence

Zhang, J., Zhang, K.

Philosophy of Science, Supplementary Volume 2015, 82(5):930-940, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

Küffner, R., Zach, N., Norel, R., Hawe, J., Schoenfeld, D., Wang, L., Li, G., Fang, L., Mackey, L., Hardiman, O., Cudkowicz, M., Sherman, A., Ertaylan, G., Grosse-Wentrup, M., Hothorn, T., van Ligtenberg, J., Macke, J., Meyer, T., Schölkopf, B., Tran, L., Vaughan, R., Stolovitzky, G., Leitner, M.

Nature Biotechnology, 33, pages: 51-57, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Probabilistic Interpretation of Linear Solvers

Hennig, P.

SIAM Journal on Optimization, 25(1):234-260, 2015 (article)

ei pn

Web PDF link (url) DOI [BibTex]

Web PDF link (url) DOI [BibTex]


no image
Developing biorobotics for veterinary research into cat movements

Mariti, C., Muscolo, G., Peters, J., Puig, D., Recchiuto, C., Sighieri, C., Solanas, A., von Stryk, O.

Journal of Veterinary Behavior: Clinical Applications and Research, 10(3):248-254, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Spatial statistics and attentional dynamics in scene viewing

Engbert, R., Trukenbrod, H., Barthelmé, S., Wichmann, F.

Journal of Vision, 15(1):1-17, 2015 (article)

ei

Web PDF link (url) DOI [BibTex]

Web PDF link (url) DOI [BibTex]


no image
The Randomized Causation Coefficient

Lopez-Paz, D., Muandet, K., Recht, B.

Journal of Machine Learning, 16, pages: 2901-2907, 2015 (article)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Towards denoising XMCD movies of fast magnetization dynamics using extended Kalman filter

Kopp, M., Harmeling, S., Schütz, G., Schölkopf, B., Fähnle, M.

Ultramicroscopy, 148, pages: 115-122, 2015 (article)

Abstract
The Kalman filter is a well-established approach to get information on the time-dependent state of a system from noisy observations. It was developed in the context of the Apollo project to see the deviation of the true trajectory of a rocket from the desired trajectory. Afterwards it was applied to many different systems with small numbers of components of the respective state vector (typically about 10). In all cases the equation of motion for the state vector was known exactly. The fast dissipative magnetization dynamics is often investigated by x-ray magnetic circular dichroism movies (XMCD movies), which are often very noisy. In this situation the number of components of the state vector is extremely large (about 105), and the equation of motion for the dissipative magnetization dynamics (especially the values of the material parameters of this equation) is not well known. In the present paper it is shown by theoretical considerations that – nevertheless – there is no principle problem for the use of the Kalman filter to denoise XMCD movies of fast dissipative magnetization dynamics.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Artificial intelligence: Learning to see and act

Schölkopf, B.

Nature, News & Views, 518(7540):486-487, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Context affects lightness at the level of surfaces

Maertens, M., Wichmann, F., Shapley, R.

Journal of Vision, 15(1):1-15, 2015 (article)

ei

Web PDF link (url) DOI [BibTex]

Web PDF link (url) DOI [BibTex]


no image
Genome-wide analysis of local chromatin packing in Arabidopsis thaliana

Wang, C., Liu, C., Roqueiro, D., Grimm, D., Schwab, R., Becker, C., Lanz, C., Weigel, D.

Genome Research, 25(2):246-256, 2015 (article)

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Segmentation-based attenuation correction in positron emission tomography/magnetic resonance: erroneous tissue identification and its impact on positron emission tomography interpretation

Brendle, C., Schmidt, H., Oergel, A., Bezrukov, I., Mueller, M., Schraml, C., Pfannenberg, C., la Fougère, C., Nikolaou, K., Schwenzer, N.

Investigative Radiology, 50(5):339-346, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Active Reward Learning with a Novel Acquisition Function

Daniel, C., Kroemer, O., Viering, M., Metz, J., Peters, J.

Autonomous Robots, 39(3):389-405, 2015 (article)

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
A systematic search for transiting planets in the K2 data

Foreman-Mackey, D., Montet, B., Hogg, D., Morton, T., Wang, D., Schölkopf, B.

The Astrophysical Journal, 806(2), 2015 (article)

Abstract
Photometry of stars from the K2 extension of NASA’s Kepler mission is afflicted by systematic effects caused by small (few-pixel) drifts in the telescope pointing and other spacecraft issues. We present a method for searching K2 light curves for evidence of exoplanets by simultaneously fitting for these systematics and the transit signals of interest. This method is more computationally expensive than standard search algorithms but we demonstrate that it can be efficiently implemented and used to discover transit signals. We apply this method to the full Campaign 1 data set and report a list of 36 planet candidates transiting 31 stars, along with an analysis of the pipeline performance and detection efficiency based on artificial signal injections and recoveries. For all planet candidates, we present posterior distributions on the properties of each system based strictly on the transit observables.

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning Movement Primitive Attractor Goals and Sequential Skills from Kinesthetic Demonstrations

Manschitz, S., Kober, J., Gienger, M., Peters, J.

Robotics and Autonomous Systems, 74, Part A, pages: 97-107, 2015 (article)

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Bayesian Optimization for Learning Gaits under Uncertainty

Calandra, R., Seyfarth, A., Peters, J., Deisenroth, M.

Annals of Mathematics and Artificial Intelligence, pages: 1-19, 2015 (article)

am ei

DOI [BibTex]

DOI [BibTex]


no image
Assessment of murine brain tissue shrinkage caused by different histological fixatives using magnetic resonance and computed tomography imaging

Wehrl, H. F., Bezrukov, I., Wiehr, S., Lehnhoff, M., Fuchs, K., Mannheim, J. G., Quintanilla-Martinez, L., Kneilling, M., Pichler, B. J., Sauter, A. W.

Histology and Histopathology, 30(5):601-613, 2015 (article)

ei

[BibTex]

[BibTex]


no image
Improved Bayesian Information Criterion for Mixture Model Selection

Mehrjou, A., Hosseini, R., Araabi, B.

Pattern Recognition Letters, 69, pages: 22-27, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Correlation matrix nearness and completion under observation uncertainty

Alaíz, C. M., Dinuzzo, F., Sra, S.

IMA Journal of Numerical Analysis, 35(1):325-340, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Quantitative evaluation of segmentation- and atlas- based attenuation correction for PET/MR on pediatric patients

Bezrukov, I., Schmidt, H., Gatidis, S., Mantlik, F., Schäfer, J. F., Schwenzer, N., Pichler, B. J.

Journal of Nuclear Medicine, 56(7):1067-1074, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Probabilistic numerics and uncertainty in computations

Hennig, P., Osborne, M. A., Girolami, M.

Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, 471(2179), 2015 (article)

Abstract
We deliver a call to arms for probabilistic numerical methods: algorithms for numerical tasks, including linear algebra, integration, optimization and solving differential equations, that return uncertainties in their calculations. Such uncertainties, arising from the loss of precision induced by numerical calculation with limited time or hardware, are important for much contemporary science and industry. Within applications such as climate science and astrophysics, the need to make decisions on the basis of computations with large and complex data have led to a renewed focus on the management of numerical uncertainty. We describe how several seminal classic numerical methods can be interpreted naturally as probabilistic inference. We then show that the probabilistic view suggests new algorithms that can flexibly be adapted to suit application specifics, while delivering improved empirical performance. We provide concrete illustrations of the benefits of probabilistic numeric algorithms on real scientific problems from astrometry and astronomical imaging, while highlighting open problems with these new algorithms. Finally, we describe how probabilistic numerical methods provide a coherent framework for identifying the uncertainty in calculations performed with a combination of numerical algorithms (e.g. both numerical optimizers and differential equation solvers), potentially allowing the diagnosis (and control) of error sources in computations.

ei pn

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Mass and galaxy distributions of four massive galaxy clusters from Dark Energy Survey Science Verification data

Melchior, P., Suchyta, E., Huff, E., Hirsch, M., Kacprzak, T., Rykoff, E., Gruen, D., Armstrong, R., Bacon, D., Bechtol, K., others,

Monthly Notices of the Royal Astronomical Society, 449(3):2219-2238, Oxford University Press, 2015 (article)

ei

DOI [BibTex]

DOI [BibTex]


no image
Kinematic and gait similarities between crawling human infants and other quadruped mammals

Righetti, L., Nylen, A., Rosander, K., Ijspeert, A.

Frontiers in Neurology, 6(17), February 2015 (article)

Abstract
Crawling on hands and knees is an early pattern of human infant locomotion, which offers an interesting way of studying quadrupedalism in one of its simplest form. We investigate how crawling human infants compare to other quadruped mammals, especially primates. We present quantitative data on both the gait and kinematics of seven 10-month-old crawling infants. Body movements were measured with an optoelectronic system giving precise data on 3-dimensional limb movements. Crawling on hands and knees is very similar to the locomotion of non-human primates in terms of the quite protracted arm at touch-down, the coordination between the spine movements in the lateral plane and the limbs, the relatively extended limbs during locomotion and the strong correlation between stance duration and speed of locomotion. However, there are important differences compared to primates, such as the choice of a lateral-sequence walking gait, which is similar to most non-primate mammals and the relatively stiff elbows during stance as opposed to the quite compliant gaits of primates. These finding raise the question of the role of both the mechanical structure of the body and neural control on the determination of these characteristics.

mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Entropic Movement Complexity Reflects Subjective Creativity Rankings of Visualized Hand Motion Trajectories

Peng, Z, Braun, DA

Frontiers in Psychology, 6(1879):1-13, December 2015 (article)

Abstract
In a previous study we have shown that human motion trajectories can be characterized by translating continuous trajectories into symbol sequences with well-defined complexity measures. Here we test the hypothesis that the motion complexity individuals generate in their movements might be correlated to the degree of creativity assigned by a human observer to the visualized motion trajectories. We asked participants to generate 55 novel hand movement patterns in virtual reality, where each pattern had to be repeated 10 times in a row to ensure reproducibility. This allowed us to estimate a probability distribution over trajectories for each pattern. We assessed motion complexity not only by the previously proposed complexity measures on symbolic sequences, but we also propose two novel complexity measures that can be directly applied to the distributions over trajectories based on the frameworks of Gaussian Processes and Probabilistic Movement Primitives. In contrast to previous studies, these new methods allow computing complexities of individual motion patterns from very few sample trajectories. We compared the different complexity measures to how a group of independent jurors rank ordered the recorded motion trajectories according to their personal creativity judgment. We found three entropic complexity measures that correlate significantly with human creativity judgment and discuss differences between the measures. We also test whether these complexity measures correlate with individual creativity in divergent thinking tasks, but do not find any consistent correlation. Our results suggest that entropic complexity measures of hand motion may reveal domain-specific individual differences in kinesthetic creativity.

ei

DOI [BibTex]

DOI [BibTex]


no image
Bounded rationality, abstraction and hierarchical decision-making: an information-theoretic optimality principle

Genewein, T, Leibfried, F, Grau-Moya, J, Braun, DA

Frontiers in Robotics and AI, 2(27):1-24, October 2015 (article)

Abstract
Abstraction and hierarchical information-processing are hallmarks of human and animal intelligence underlying the unrivaled flexibility of behavior in biological systems. Achieving such a flexibility in artificial systems is challenging, even with more and more computational power. Here we investigate the hypothesis that abstraction and hierarchical information-processing might in fact be the consequence of limitations in information-processing power. In particular, we study an information-theoretic framework of bounded rational decision-making that trades off utility maximization against information-processing costs. We apply the basic principle of this framework to perception-action systems with multiple information-processing nodes and derive bounded optimal solutions. We show how the formation of abstractions and decision-making hierarchies depends on information-processing costs. We illustrate the theoretical ideas with example simulations and conclude by formalizing a mathematically unifying optimization principle that could potentially be extended to more complex systems.

ei

DOI [BibTex]

DOI [BibTex]


no image
Signaling equilibria in sensorimotor interactions

Leibfried, F, Grau-Moya, J, Braun, DA

Cognition, 141, pages: 73-86, August 2015 (article)

Abstract
Although complex forms of communication like human language are often assumed to have evolved out of more simple forms of sensorimotor signaling, less attention has been devoted to investigate the latter. Here, we study communicative sensorimotor behavior of humans in a two-person joint motor task where each player controls one dimension of a planar motion. We designed this joint task as a game where one player (the sender) possesses private information about a hidden target the other player (the receiver) wants to know about, and where the sender's actions are costly signals that influence the receiver's control strategy. We developed a game-theoretic model within the framework of signaling games to investigate whether subjects' behavior could be adequately described by the corresponding equilibrium solutions. The model predicts both separating and pooling equilibria, in which signaling does and does not occur respectively. We observed both kinds of equilibria in subjects and found that, in line with model predictions, the propensity of signaling decreased with increasing signaling costs and decreasing uncertainty on the part of the receiver. Our study demonstrates that signaling games, which have previously been applied to economic decision-making and animal communication, provide a framework for human signaling behavior arising during sensorimotor interactions in continuous and dynamic environments.

ei

DOI [BibTex]

DOI [BibTex]


no image
Structure Learning in Bayesian Sensorimotor Integration

Genewein, T, Hez, E, Razzaghpanah, Z, Braun, DA

PLoS Computational Biology, 11(8):1-27, August 2015 (article)

Abstract
Previous studies have shown that sensorimotor processing can often be described by Bayesian learning, in particular the integration of prior and feedback information depending on its degree of reliability. Here we test the hypothesis that the integration process itself can be tuned to the statistical structure of the environment. We exposed human participants to a reaching task in a three-dimensional virtual reality environment where we could displace the visual feedback of their hand position in a two dimensional plane. When introducing statistical structure between the two dimensions of the displacement, we found that over the course of several days participants adapted their feedback integration process in order to exploit this structure for performance improvement. In control experiments we found that this adaptation process critically depended on performance feedback and could not be induced by verbal instructions. Our results suggest that structural learning is an important meta-learning component of Bayesian sensorimotor integration.

ei

DOI [BibTex]

DOI [BibTex]


no image
A Reward-Maximizing Spiking Neuron as a Bounded Rational Decision Maker

Leibfried, F, Braun, DA

Neural Computation, 27(8):1686-1720, July 2015 (article)

Abstract
Rate distortion theory describes how to communicate relevant information most efficiently over a channel with limited capacity. One of the many applications of rate distortion theory is bounded rational decision making, where decision makers are modeled as information channels that transform sensory input into motor output under the constraint that their channel capacity is limited. Such a bounded rational decision maker can be thought to optimize an objective function that trades off the decision maker's utility or cumulative reward against the information processing cost measured by the mutual information between sensory input and motor output. In this study, we interpret a spiking neuron as a bounded rational decision maker that aims to maximize its expected reward under the computational constraint that the mutual information between the neuron's input and output is upper bounded. This abstract computational constraint translates into a penalization of the deviation between the neuron's instantaneous and average firing behavior. We derive a synaptic weight update rule for such a rate distortion optimizing neuron and show in simulations that the neuron efficiently extracts reward-relevant information from the input by trading off its synaptic strengths against the collected reward.

ei

DOI [BibTex]

DOI [BibTex]


no image
What is epistemic value in free energy models of learning and acting? A bounded rationality perspective

Ortega, PA, Braun, DA

Cognitive Neuroscience, 6(4):215-216, December 2015 (article)

Abstract
Free energy models of learning and acting do not only care about utility or extrinsic value, but also about intrinsic value, that is, the information value stemming from probability distributions that represent beliefs or strategies. While these intrinsic values can be interpreted as epistemic values or exploration bonuses under certain conditions, the framework of bounded rationality offers a complementary interpretation in terms of information-processing costs that we discuss here.

ei

DOI [BibTex]

DOI [BibTex]

2013


no image
Correlation of Simultaneously Acquired Diffusion-Weighted Imaging and 2-Deoxy-[18F] fluoro-2-D-glucose Positron Emission Tomography of Pulmonary Lesions in a Dedicated Whole-Body Magnetic Resonance/Positron Emission Tomography System

Schmidt, H., Brendle, C., Schraml, C., Martirosian, P., Bezrukov, I., Hetzel, J., Müller, M., Sauter, A., Claussen, C., Pfannenberg, C., Schwenzer, N.

Investigative Radiology, 48(5):247-255, May 2013 (article)

ei

Web [BibTex]

2013


Web [BibTex]


no image
Replacing Causal Faithfulness with Algorithmic Independence of Conditionals

Lemeire, J., Janzing, D.

Minds and Machines, 23(2):227-249, May 2013 (article)

Abstract
Independence of Conditionals (IC) has recently been proposed as a basic rule for causal structure learning. If a Bayesian network represents the causal structure, its Conditional Probability Distributions (CPDs) should be algorithmically independent. In this paper we compare IC with causal faithfulness (FF), stating that only those conditional independences that are implied by the causal Markov condition hold true. The latter is a basic postulate in common approaches to causal structure learning. The common spirit of FF and IC is to reject causal graphs for which the joint distribution looks ‘non-generic’. The difference lies in the notion of genericity: FF sometimes rejects models just because one of the CPDs is simple, for instance if the CPD describes a deterministic relation. IC does not behave in this undesirable way. It only rejects a model when there is a non-generic relation between different CPDs although each CPD looks generic when considered separately. Moreover, it detects relations between CPDs that cannot be captured by conditional independences. IC therefore helps in distinguishing causal graphs that induce the same conditional independences (i.e., they belong to the same Markov equivalence class). The usual justification for FF implicitly assumes a prior that is a probability density on the parameter space. IC can be justified by Solomonoff’s universal prior, assigning non-zero probability to those points in parameter space that have a finite description. In this way, it favours simple CPDs, and therefore respects Occam’s razor. Since Kolmogorov complexity is uncomputable, IC is not directly applicable in practice. We argue that it is nevertheless helpful, since it has already served as inspiration and justification for novel causal inference algorithms.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
What can neurons do for their brain? Communicate selectivity with bursts

Balduzzi, D., Tononi, G.

Theory in Biosciences , 132(1):27-39, Springer, March 2013 (article)

Abstract
Neurons deep in cortex interact with the environment extremely indirectly; the spikes they receive and produce are pre- and post-processed by millions of other neurons. This paper proposes two information-theoretic constraints guiding the production of spikes, that help ensure bursting activity deep in cortex relates meaningfully to events in the environment. First, neurons should emphasize selective responses with bursts. Second, neurons should propagate selective inputs by burst-firing in response to them. We show the constraints are necessary for bursts to dominate information-transfer within cortex, thereby providing a substrate allowing neurons to distribute credit amongst themselves. Finally, since synaptic plasticity degrades the ability of neurons to burst selectively, we argue that homeostatic regulation of synaptic weights is necessary, and that it is best performed offline during sleep.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Apprenticeship Learning with Few Examples

Boularias, A., Chaib-draa, B.

Neurocomputing, 104, pages: 83-96, March 2013 (article)

Abstract
We consider the problem of imitation learning when the examples, provided by an expert human, are scarce. Apprenticeship learning via inverse reinforcement learning provides an efficient tool for generalizing the examples, based on the assumption that the expert's policy maximizes a value function, which is a linear combination of state and action features. Most apprenticeship learning algorithms use only simple empirical averages of the features in the demonstrations as a statistics of the expert's policy. However, this method is efficient only when the number of examples is sufficiently large to cover most of the states, or the dynamics of the system is nearly deterministic. In this paper, we show that the quality of the learned policies is sensitive to the error in estimating the averages of the features when the dynamics of the system is stochastic. To reduce this error, we introduce two new approaches for bootstrapping the demonstrations by assuming that the expert is near-optimal and the dynamics of the system is known. In the first approach, the expert's examples are used to learn a reward function and to generate furthermore examples from the corresponding optimal policy. The second approach uses a transfer technique, known as graph homomorphism, in order to generalize the expert's actions to unvisited regions of the state space. Empirical results on simulated robot navigation problems show that our approach is able to learn sufficiently good policies from a significantly small number of examples.

ei

Web DOI [BibTex]

Web DOI [BibTex]


Thumb xl thumb hennigk2012 2
Quasi-Newton Methods: A New Direction

Hennig, P., Kiefel, M.

Journal of Machine Learning Research, 14(1):843-865, March 2013 (article)

Abstract
Four decades after their invention, quasi-Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.

ei ps pn

website+code pdf link (url) [BibTex]

website+code pdf link (url) [BibTex]


no image
Regional effects of magnetization dispersion on quantitative perfusion imaging for pulsed and continuous arterial spin labeling

Cavusoglu, M., Pohmann, R., Burger, H. C., Uludag, K.

Magnetic Resonance in Medicine, 69(2):524-530, Febuary 2013 (article)

Abstract
Most experiments assume a global transit delay time with blood flowing from the tagging region to the imaging slice in plug flow without any dispersion of the magnetization. However, because of cardiac pulsation, nonuniform cross-sectional flow profile, and complex vessel networks, the transit delay time is not a single value but follows a distribution. In this study, we explored the regional effects of magnetization dispersion on quantitative perfusion imaging for varying transit times within a very large interval from the direct comparison of pulsed, pseudo-continuous, and dual-coil continuous arterial spin labeling encoding schemes. Longer distances between tagging and imaging region typically used for continuous tagging schemes enhance the regional bias on the quantitative cerebral blood flow measurement causing an underestimation up to 37% when plug flow is assumed as in the standard model.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
The multivariate Watson distribution: Maximum-likelihood estimation and other aspects

Sra, S., Karp, D.

Journal of Multivariate Analysis, 114, pages: 256-269, February 2013 (article)

Abstract
This paper studies fundamental aspects of modelling data using multivariate Watson distributions. Although these distributions are natural for modelling axially symmetric data (i.e., unit vectors where View the MathML source are equivalent), for high-dimensions using them can be difficult—largely because for Watson distributions even basic tasks such as maximum-likelihood are numerically challenging. To tackle the numerical difficulties some approximations have been derived. But these are either grossly inaccurate in high-dimensions [K.V. Mardia, P. Jupp, Directional Statistics, second ed., John Wiley & Sons, 2000] or when reasonably accurate [A. Bijral, M. Breitenbach, G.Z. Grudic, Mixture of Watson distributions: a generative model for hyperspherical embeddings, in: Artificial Intelligence and Statistics, AISTATS 2007, 2007, pp. 35–42], they lack theoretical justification. We derive new approximations to the maximum-likelihood estimates; our approximations are theoretically well-defined, numerically accurate, and easy to compute. We build on our parameter estimation and discuss mixture-modelling with Watson distributions; here we uncover a hitherto unknown connection to the “diametrical clustering” algorithm of Dhillon et al. [I.S. Dhillon, E.M. Marcotte, U. Roshan, Diametrical clustering for identifying anticorrelated gene clusters, Bioinformatics 19 (13) (2003) 1612–1619].

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
How the result of graph clustering methods depends on the construction of the graph

Maier, M., von Luxburg, U., Hein, M.

ESAIM: Probability & Statistics, 17, pages: 370-418, January 2013 (article)

Abstract
We study the scenario of graph-based clustering algorithms such as spectral clustering. Given a set of data points, one rst has to construct a graph on the data points and then apply a graph clustering algorithm to nd a suitable partition of the graph. Our main question is if and how the construction of the graph (choice of the graph, choice of parameters, choice of weights) in uences the outcome of the nal clustering result. To this end we study the convergence of cluster quality measures such as the normalized cut or the Cheeger cut on various kinds of random geometric graphs as the sample size tends to in nity. It turns out that the limit values of the same objective function are systematically di erent on di erent types of graphs. This implies that clustering results systematically depend on the graph and can be very di erent for di erent types of graph. We provide examples to illustrate the implications on spectral clustering.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Explicit eigenvalues of certain scaled trigonometric matrices

Sra, S.

Linear Algebra and its Applications, 438(1):173-181, January 2013 (article)

ei

DOI [BibTex]

DOI [BibTex]