While human listeners excel at selectively attending to a conversation in a cocktail party, machine performance is still far inferior by comparison. We show that the cocktail party problem, or the speech separation problem, can be effectively approached via structured prediction. To account for temporal dynamics in speech, we employ conditional random fields (CRFs) to classify speech dominance within each time-frequency unit for a sound mixture. To capture complex, nonlinear relationship between input and output, both state and transition feature functions in CRFs are learned by deep neural networks. The formulation of the problem as classification allows us to directly optimize a measure that is well correlated with human speech intelligibility. The proposed system substantially outperforms existing ones in a variety of noises.

The Shape Boltzmann Machine (SBM) has recently been introduced as a state-of-the-art model of foreground/background object shape. We extend the SBM to account for the foreground object's parts. Our model, the Multinomial SBM (MSBM), can capture both local and global statistics of part shapes accurately. We combine the MSBM with an appearance model to form a fully generative model of images of objects. Parts-based image segmentations are obtained simply by performing probabilistic inference in the model. We apply the model to two challenging datasets which exhibit significant shape and appearance variability, and find that it obtains results that are comparable to the state-of-the-art.

In this paper, we derive a novel algorithm to cluster hidden Markov models (HMMs) according to their probability distributions. We propose a variational hierarchical EM algorithm that i) clusters a given collection of HMMs into groups of HMMs that are similar, in terms of the distributions they represent, and ii) characterizes each group by a ``cluster center'', i.e., a novel HMM that is representative for the group. We illustrate the benefits of the proposed algorithm on hierarchical clustering of motion capture sequences as well as on automatic music tagging.

This paper introduces timeline trees, which are partial models of partially observable environments. Timeline trees are given some specific predictions to make and learn a decision tree over history. The main idea of timeline trees is to use temporally abstract features to identify and split on features of key events, spread arbitrarily far apart in the past (whereas previous decision-tree-based methods have been limited to a finite suffix of history). Experiments demonstrate that timeline trees can learn to make high quality predictions in complex, partially observable environments with high-dimensional observations (e.g. an arcade game).

We uncover relations between robust MDPs and risk-sensitive MDPs. The objective of a robust MDP is to minimize a function, such as the expectation of cumulative cost, for the worst case when the parameters have uncertainties. The objective of a risk-sensitive MDP is to minimize a risk measure of the cumulative cost when the parameters are known. We show that a risk-sensitive MDP of minimizing the expected exponential utility is equivalent to a robust MDP of minimizing the worst-case expectation with a penalty for the deviation of the uncertain parameters from their nominal values, which is measured with the Kullback-Leibler divergence. We also show that a risk-sensitive MDP of minimizing an iterated risk measure that is composed of certain coherent risk measures is equivalent to a robust MDP of minimizing the worst-case expectation when the possible deviations of uncertain parameters from their nominal values are characterized with a concave function.

Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real world images has required the careful selection of feature representation based on hand-crafted image descriptors, in order to achieve an appropriate, smooth optimization landscape. In this paper, we instead propose a novel combination of unsupervised joint alignment with unsupervised feature learning. Specifically, we incorporate deep learning into the {\em congealing} alignment framework. Through deep learning, we obtain features that can represent the image at differing resolutions based on network depth, and that are tuned to the statistics of the specific data being aligned. In addition, we modify the learning algorithm for the restricted Boltzmann machine by incorporating a group sparsity penalty, leading to a topographic organization on the learned filters and improving subsequent alignment results. We apply our method to the Labeled Faces in the Wild database (LFW). Using the aligned images produced by our proposed unsupervised algorithm, we achieve a significantly higher accuracy in face verification than obtained using the original face images, prior work in unsupervised alignment, and prior work in supervised alignment. We also match the accuracy for the best available, but unpublished method.

The partition function plays a key role in probabilistic modeling including conditional random fields, graphical models, and maximum likelihood estimation. To optimize partition functions, this article introduces a quadratic variational upper bound. This inequality facilitates majorization methods: optimization of complicated functions through the iterative solution of simpler sub-problems. Such bounds remain efficient to compute even when the partition function involves a graphical model (with small tree-width) or in latent likelihood settings. For large-scale problems, low-rank versions of the bound are provided and outperform LBFGS as well as first-order methods. Several learning applications are shown and reduce to fast and convergent update rules. Experimental results show advantages over state-of-the-art optimization methods.

In a large visual multi-class detection framework, the timeliness of results can be crucial. Our method for timely multi-class detection aims to give the best possible performance at any single point after a start time; it is terminated at a deadline time. Toward this goal, we formulate a dynamic, closed-loop policy that infers the contents of the image in order to decide which detector to deploy next. In contrast to previous work, our method significantly diverges from the predominant greedy strategies, and is able to learn to take actions with deferred values. We evaluate our method with a novel timeliness measure, computed as the area under an Average Precision vs. Time curve. Experiments are conducted on the eminent PASCAL VOC object detection dataset. If execution is stopped when only half the detectors have been run, our method obtains $66\%$ better AP than a random ordering, and $14\%$ better performance than an intelligent baseline. On the timeliness measure, our method obtains at least $11\%$ better performance. Our code, to be made available upon publication, is easily extensible as it treats detectors and classifiers as black boxes and learns from execution traces using reinforcement learning.

Given a current news event, we tackle the problem of generating plausible predictions of future events it might cause. We present a new methodology for modeling and predicting such future news events using machine learning and data mining techniques. Our Pundit algorithm generalizes examples of causality pairs to infer a causality predictor. To obtain precisely labeled causality examples, we mine 150 years of news articles and apply semantic natural language modeling techniques to headlines containing certain predefined causality patterns. For generalization, the model uses a vast number of world knowledge ontologies. Empirical evaluation on real news articles shows that our Pundit algorithm performs as well as non-expert humans.

We consider online planning in Markov decision processes (MDPs). In online planning, the agent focuses on its current state only, deliberates about the set of possible policies from that state onwards and, when interrupted, uses the outcome of that exploratory deliberation to choose what action to perform next. The performance of algorithms for online planning is assessed in terms of simple regret, which is the agent's expected performance loss when the chosen action, rather than an optimal one, is followed. To date, state-of-the-art algorithms for online planning in general MDPs are either best effort, or guarantee only polynomial-rate reduction of simple regret over time. Here we introduce a new Monte-Carlo tree search algorithm, BRUE, that guarantees exponential-rate reduction of simple regret and error probability. This algorithm is based on a simple yet non-standard state-space sampling scheme, MCTS2e, in which different parts of each sample are dedicated to different exploratory objectives. Our empirical evaluation shows that BRUE not only provides superior performance guarantees, but is also very effective in practice and favorably compares to state-of-the-art. We then extend BRUE with a variant of "learning by forgetting." The resulting set of algorithms, BRUE(alpha), generalizes BRUE, improves the exponential factor in the upper bound on its reduction rate, and exhibits even more attractive empirical performance.