The principle of maximum entropy (MaxEnt) constitutes a powerful formalism for nonmonotonic reasoning based on probabilistic conditionals. Conditionals are defeasible rules which allow one to express that certain subclasses of some broader concept behave exceptional. In the (common) probabilistic semantics of conditional statements, these exceptions are formalized only implicitly: The conditional (B|A)[p] expresses that if A holds, then B is typically true, namely with probability p, but without explicitly talking about the subclass of A for which B does not hold. There is no possibility to express within the conditional that a subclass C of A is excluded from the inference to B because one is unaware of the probability of B given C. In this paper, we apply the concept of default negation to probabilistic MaxEnt reasoning in order to formalize this kind of unawareness and propose a context-based inference formalism. We exemplify the usefulness of this inference relation, and show that it satisfies basic formal properties of probabilistic reasoning.

Training conditional maximum entropy models on massive data requires significant time and computational resources. In this paper, we investigate three common distributed training strategies: distributed gradient, majority voting ensembles, and parameter mixtures. We analyze the worst-case runtime and resource costs of each and present a theoretical foundation for the convergence of parameters under parameter mixtures, the most efficient strategy. We present large-scale experiments comparing the different strategies and demonstrate that parameter mixtures over independent models use fewer resources and achieve comparable loss as compared to standard approaches. Papers published at the Neural Information Processing Systems Conference.

We develop a new algorithm for online planning in large scale sequential decision problems that improves upon the worst case efficiency of UCT. The idea is to augment Monte-Carlo Tree Search (MCTS) with maximum entropy policy optimization, evaluating each search node by softmax values back-propagated from simulation. To establish the effectiveness of this approach, we first investigate the single-step decision problem, stochastic softmax bandits, and show that softmax values can be estimated at an optimal convergence rate in terms of mean squared error. We then extend this approach to general sequential decision making by developing a general MCTS algorithm, Maximum Entropy for Tree Search (MENTS). We prove that the probability of MENTS failing to identify the best decision at the root decays exponentially, which fundamentally improves the polynomial convergence rate of UCT.

Second-order maximum-entropy models have recently gained much interest for describing the statistics of binary spike trains. Here, we extend this approach to take continuous stimuli into account as well. By constraining the joint second-order statistics, we obtain a joint Gaussian-Boltzmann distribution of continuous stimuli and binary neural firing patterns, for which we also compute marginal and conditional distributions. This model has the same computational complexity as pure binary models and fitting it to data is a convex problem. We show that the model can be seen as an extension to the classical spike-triggered average/covariance analysis and can be used as a non-linear method for extracting features which a neural population is sensitive to.

Maximum entropy models have become popular statistical models in neuroscience and other areas in biology, and can be useful tools for obtaining estimates of mu- tual information in biological systems. However, maximum entropy models fit to small data sets can be subject to sampling bias; i.e. the true entropy of the data can be severely underestimated. Here we study the sampling properties of estimates of the entropy obtained from maximum entropy models. We show that if the data is generated by a distribution that lies in the model class, the bias is equal to the number of parameters divided by twice the number of observations. However, in practice, the true distribution is usually outside the model class, and we show here that this misspecification can lead to much larger bias.

The application of the maximum entropy principle to sequence modeling has been popularized by methods such as Conditional Random Fields (CRFs). However, these approaches are generally limited to modeling paths in discrete spaces of low dimensionality. We consider the problem of modeling distributions over paths in continuous spaces of high dimensionality---a problem for which inference is generally intractable. Our main contribution is to show that maximum entropy modeling of high-dimensional, continuous paths is tractable as long as the constrained features possess a certain kind of low dimensional structure. In this case, we show that the associated {\em partition function} is symmetric and that this symmetry can be exploited to compute the partition function efficiently in a compressed form.

The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family has been very popular in machine learning due to its "Occam's razor" interpretation. Unfortunately, calculating the potentials in the maximum entropy distribution is intractable [BGS14]. We provide computationally efficient versions of this principle when the mean parameters are pairwise moments: we design distributions that approximately match given pairwise moments, while having entropy which is comparable to the maximum entropy distribution matching those moments. We additionally provide surprising applications of the approximate maximum entropy principle to designing provable variational methods for partition function calculations for Ising models without any assumptions on the potentials of the model. More precisely, we show that we can get approximation guarantees for the log-partition function comparable to those in the low-temperature limit, which is the setting of optimization of quadratic forms over the hypercube.

Connectionist Temporal Classification (CTC) is an objective function for end-to-end sequence learning, which adopts dynamic programming algorithms to directly learn the mapping between sequences. CTC has shown promising results in many sequence learning applications including speech recognition and scene text recognition. However, CTC tends to produce highly peaky and overconfident distributions, which is a symptom of overfitting. To remedy this, we propose a regularization method based on maximum conditional entropy which penalizes peaky distributions and encourages exploration. We also introduce an entropy-based pruning method to dramatically reduce the number of CTC feasible paths by ruling out unreasonable alignments. Experiments on scene text recognition show that our proposed methods consistently improve over the CTC baseline without the need to adjust training settings.

Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data. Utilizing this notion of small visual diversity, we revisit Maximum-Entropy learning in the context of fine-grained classification, and provide a training routine that maximizes the entropy of the output probability distribution for training convolutional neural networks on FGVC tasks. We provide a theoretical as well as empirical justification of our approach, and achieve state-of-the-art performance across a variety of classification tasks in FGVC, that can potentially be extended to any fine-tuning task. Our method is robust to different hyperparameter values, amount of training data and amount of training label noise and can hence be a valuable tool in many similar problems. Papers published at the Neural Information Processing Systems Conference.

The optimal policy of a reinforcement learning problem is often discontinuous and non-smooth. I.e., for two states with similar representations, their optimal policies can be significantly different. In this case, representing the entire policy with a function approximator (FA) with shared parameters for all states maybe not desirable, as the generalization ability of parameters sharing makes representing discontinuous, non-smooth policies difficult. A common way to solve this problem, known as Mixture-of-Experts, is to represent the policy as the weighted sum of multiple components, where different components perform well on different parts of the state space. Following this idea and inspired by a recent work called advantage-weighted information maximization, we propose to learn for each state weights of these components, so that they entail the information of the state itself and also the preferred action learned so far for the state. The action preference is characterized via the advantage function. In this case, the weight of each component would only be large for certain groups of states whose representations are similar and preferred action representations are also similar. Therefore each component is easy to be represented. We call a policy parameterized in this way an Advantage Weighted Mixture Policy (AWMP) and apply this idea to improve soft-actor-critic (SAC), one of the most competitive continuous control algorithm. Experimental results demonstrate that SAC with AWMP clearly outperforms SAC in four commonly used continuous control tasks and achieve stable performance across different random seeds.