We consider methods that try to find a good policy for a Markov decision process by choosing one from a given class. The policy is chosen based on its empirical performance in simulations. We are interested in conditions on the complexity of the policy class that ensure the success of such simulation based policy search methods. We show that under bounds on the amount of computation involved in computing policies, transition dynamics and rewards, uniform convergence of empirical estimates to true value functions occurs. Previously, such results were derived by assuming boundedness of pseudodimension and Lipschitz continuity. These assumptions and ours are both stronger than the usual combinatorial complexity measures.We show, via minimax inequalities, that this is essential: boundedness of pseudodimension or fat-shattering dimension alone is not sufficient.

We present a method for localizing and separating sound sources in stereo recordings thatis robust to reverberation and does not make any assumptions about the source statistics. The method consists of a probabilistic model of binaural multisource recordingsand an expectation maximization algorithm for finding the maximum likelihood parameters of that model. These parameters include distributions over delays and assignments of time-frequency regions to sources. We evaluate this method against two comparable algorithms on simulations of simultaneous speech from two or three sources. Our method outperforms the others in anechoic conditionsand performs as well as the better of the two in the presence of reverberation.

Maximizing the efficiency of data collection is important in any experimental setting.

For example, muscleresponse can change because of fatigue, a condition where the disturbance has a fast timescale or because of disease where the disturbance is much slower. Here we hypothesize that the nervous system adapts in a way that reflects the temporal properties of such potential disturbances. According to a Bayesian formulation of this idea, movement error results in a credit assignment problem:what timescale is responsible for this disturbance? The adaptation schedule influences the behavior of the optimal learner, changing estimates at different timescalesas well as the uncertainty. A system that adapts in this way predicts many properties observed in saccadic gain adaptation. It well predicts the timecourses of motor adaptation in cases of partial sensory deprivation and reversals of the adaptation direction.

This question reflects one fundamental aspect of "bounded rationality," a

We consider the problem of inferring the structure of a network from cooccurrence data:observations that indicate which nodes occur in a signaling pathway but do not directly reveal node order within the pathway. This problem is motivated by network inference problems arising in computational biology and communication systems, in which it is difficult or impossible to obtain precise time ordering information. Without order information, every permutation of the activated nodes leads to a different feasible solution, resulting in combinatorial explosion of the feasible set. However, physical principles underlying most networked systemssuggest that not all feasible solutions are equally likely. Intuitively, nodes that cooccur more frequently are probably more closely connected. Building on this intuition, we model path co-occurrences as randomly shuffled samples of a random walk on the network. We derive a computationally efficient network inference algorithm and, via novel concentration inequalities for importance samplingestimators, prove that a polynomial complexity Monte Carlo version of the algorithm converges with high probability.

The performance of EEGbased Brain-Computer-Interfaces (BCIs) critically depends onthe extraction of features from the EEG carrying information relevant for the classification of different mental states. For BCIs employing imaginary movements of different limbs, the method of Common Spatial Patterns (CSP) has been shown to achieve excellent classification results.

In this paper, we generalize the previous iLSTD algorithm and present three new results: (1)the first convergence proof for an iLSTD algorithm; (2) an extension to incorporate eligibility traces without changing the asymptotic computational complexity; and(3) the first empirical results with an iLSTD algorithm for a problem (mountain car) with feature vectors large enough (n 10, 000) to show substantial computationaladvantages over LSTD.

The quality measures used in information retrieval are particularly difficult to optimize directly,since they depend on the model scores only through the sorted order of the documents returned for a given query. Thus, the derivatives of the cost with respect to the model parameters are either zero, or are undefined. In this paper, we propose a class of simple, flexible algorithms, called LambdaRank, which avoids these difficulties by working with implicit cost functions. We describe LambdaRankusing neural network models, although the idea applies to any differentiable function class. We give necessary and sufficient conditions for the resulting implicit cost function to be convex, and we show that the general method has a simple mechanical interpretation. We demonstrate significantly improved accuracy,over a state-of-the-art ranking algorithm, on several datasets. We also show that LambdaRank provides a method for significantly speeding up the training phase of that ranking algorithm. Although this paper is directed towards ranking, the proposed method can be extended to any non-smooth and multivariate cost functions.

We consider the problem of detecting humans and classifying their pose from a single image. Specifically, our goal is to devise a statistical model that simultaneously answerstwo questions: 1) is there a human in the image?