We study a new, model-free form of approximate policy iteration which uses Sarsa updates with linear state-action value function approximation for policy evaluation, and a "policy improvement operator" to generate a new policy based on the learned state-action values. We prove that if the policy improvement operator produces -soft policies and is Lipschitz continuous in the action values, with a constant that is not too large, then the approximate policy iteration algorithm converges to a unique solution from any initial policy. To our knowledge, this is the first convergence result for any form of approximate policy iteration under similar computational-resource assumptions.

Greedy importance sampling is an unbiased estimation technique that reduces the variance of standard importance sampling by explicitly searching for modes in the estimation objective. Previous work has demonstrated the feasibility of implementing this method and proved that the technique is unbiased in both discrete and continuous domains. In this paper we present a reformulation of greedy importance sampling that eliminates the free parameters from the original estimator, and introduces a new regularization strategy that further reduces variance without compromising unbiasedness. The resulting estimator is shown to be effective for difficult estimation problems arising in Markov random field inference. In particular, improvements are achieved over standard MCMC estimators when the distribution has multiple peaked modes.

In this paper we show how the generation of documents can be thought of as a k-stage Markov process, which leads to a Fisher kernel from which the n-gram and string kernels can be reconstructed. The Fisher kernel view gives a more flexible insight into the string kernel and suggests how it can be parametrised in a way that reflects the statistics of the training corpus. Furthermore, the probabilistic modelling approach suggests extending the Markov process to consider subsequences of varying length, rather than the standard fixed-length approach used in the string kernel. We give a procedure for determining which subsequences are informative features and hence generate a Finite State Machine model, which can again be used to obtain a Fisher kernel. By adjusting the parametrisation we can also influence the weighting received by the features. In this way we are able to obtain a logarithmic weighting in a Fisher kernel. Finally, experiments are reported comparing the different kernels using the standard Bag of Words kernel as a baseline.

According to a series of influential models, dopamine (DA) neurons signal reward prediction error using a temporal-difference (TD) algorithm. We address a problem not convincingly solved in these accounts: how to maintain a representation of cues that predict delayed consequences. Our new model uses a TD rule grounded in partially observable semi-Markov processes, a formalism that captures two largely neglected features of DA experiments: hidden state and temporal variability. Previous models predicted rewards using a tapped delay line representation of sensory inputs; we replace this with a more active process of inference about the underlying state of the world. The DA system can then learn to map these inferred states to reward predictions using TD. The new model can explain previously vexing data on the responses of DA neurons in the face of temporal variability. By combining statistical model-based learning with a physiologically grounded TD theory, it also brings into contact with physiology some insights about behavior that had previously been confined to more abstract psychological models.

We describe a method for learning sparse multiscale image representations using a sparse prior distribution over the basis function coefficients. The prior consists of a mixture of a Gaussian and a Dirac delta function, and thus encourages coefficients to have exact zero values. Coefficients for an image are computed by sampling from the resulting posterior distribution with a Gibbs sampler. The learned basis is similar to the Steerable Pyramid basis, and yields slightly higher SNR for the same number of active coefficients. Denoising using the learned image model is demonstrated for some standard test images, with results that compare favorably with other denoising methods.

Well-known applications include part-of-speech (POS) tagging, named entity classification, information extraction, text segmentation and phoneme classification in text and speech processing [7] as well as problems like protein homology detection, secondary structure prediction or gene classification in computational biology [3]. Up to now, the predominant formalism for modeling and predicting label sequences has been based on Hidden Markov Models (HMMs) and variations thereof. Yet, despite its success, generative probabilistic models - of which HMMs are a special case - have two major shortcomings, which this paper is not the first one to point out. First, generative probabilistic models are typically trained using maximum likelihood estimation (MLE) for a joint sampling model of observation and label sequences. As has been emphasized frequently, MLE based on the joint probability model is inherently non-discriminative and thus may lead to suboptimal prediction accuracy. Secondly, efficient inference and learning in this setting often requires to make questionable conditional independence assumptions.

We develop and test new machine learning methods for the prediction of topological representations of protein structures in the form of coarse-or fine-grained contact or distance maps that are translation and rotation invariant. The methods are based on generalized input-output hidden Markov models (GIOHMMs) and generalized recursive neural networks (GRNNs). The methods are used to predict topology directly in the fine-grained case and, in the coarsegrained case, indirectly by first learning how to score candidate graphs and then using the scoring function to search the space of possible configurations. Computer simulations show that the predictors achieve state-of-the-art performance.

We examine the problem of generating state-space compressions of POMDPs in a way that minimally impacts decision quality. We analyze the impact of compressions on decision quality, observing that compressions that allow accurate policy evaluation (prediction of expected future reward) will not affect decision quality. We derive a set of sufficient conditions that ensure accurate prediction in this respect, illustrate interesting mathematical properties these confer on lossless linear compressions, and use these to derive an iterative procedure for finding good linear lossy compressions. We also elaborate on how structured representations of a POMDP can be used to find such compressions.

Greedy importance sampling is an unbiased estimation technique that reduces the variance of standard importance sampling by explicitly searching for modes in the estimation objective. Previous work has demonstrated the feasibility of implementing this method and proved that the technique is unbiased in both discrete and continuous domains. In this paper we present a reformulation of greedy importance sampling that eliminates the free parameters from the original estimator, and introduces a new regularization strategy that further reduces variance without compromising unbiasedness. The resulting estimator is shown to be effective for difficult estimation problems arising in Markov random field inference. In particular, improvements are achieved over standard MCMC estimators when the distribution has multiple peaked modes.

We explore the consequences of viewing semantic association as the result of attempting to predict the concepts likely to arise in a particular context. We argue that the success of existing accounts of semantic representation comes as a result of indirectly addressing this problem, and show that a closer correspondence to human data can be obtained by taking a probabilistic approach that explicitly models the generative structure of language.