We propose a graphical model for representing networks of stochastic processes, the minimal generative model graph. It is based on reduced factorizations of the joint distribution over time. We show that under appropriate conditions, it is unique and consistent with another type of graphical model, the directed information graph, which is based on a generalization of Granger causality. We demonstrate how directed information quantifies Granger causality in a particular sequential prediction setting. We also develop efficient methods to estimate the topological structure from data that obviate estimating the joint statistics. One algorithm assumes upper-bounds on the degrees and uses the minimal dimension statistics necessary. In the event that the upper-bounds are not valid, the resulting graph is nonetheless an optimal approximation. Another algorithm uses near-minimal dimension statistics when no bounds are known but the distribution satisfies a certain criterion. Analogous to how structure learning algorithms for undirected graphical models use mutual information estimates, these algorithms use directed information estimates. We characterize the sample-complexity of two plug-in directed information estimators and obtain confidence intervals. For the setting when point estimates are unreliable, we propose an algorithm that uses confidence intervals to identify the best approximation that is robust to estimation error. Lastly, we demonstrate the effectiveness of the proposed algorithms through analysis of both synthetic data and real data from the Twitter network. In the latter case, we identify which news sources influence users in the network by merely analyzing tweet times.

We propose an inference method to estimate sparse interactions and biases according to Boltzmann machine learning. The basis of this method is $L_1$ regularization, which is often used in compressed sensing, a technique for reconstructing sparse input signals from undersampled outputs. $L_1$ regularization impedes the simple application of the gradient method, which optimizes the cost function that leads to accurate estimations, owing to the cost function's lack of smoothness. In this study, we utilize the majorizer minimization method, which is a well-known technique implemented in optimization problems, to avoid the non-smoothness of the cost function. By using the majorizer minimization method, we elucidate essentially relevant biases and interactions from given data with seemingly strongly-correlated components.

Despite having various attractive qualities such as high prediction accuracy and the ability to quantify uncertainty and avoid over-fitting, Bayesian Matrix Factorization has not been widely adopted because of the prohibitive cost of inference. In this paper, we propose a scalable distributed Bayesian matrix factorization algorithm using stochastic gradient MCMC. Our algorithm, based on Distributed Stochastic Gradient Langevin Dynamics, can not only match the prediction accuracy of standard MCMC methods like Gibbs sampling, but at the same time is as fast and simple as stochastic gradient descent. In our experiments, we show that our algorithm can achieve the same level of prediction accuracy as Gibbs sampling an order of magnitude faster. We also show that our method reduces the prediction error as fast as distributed stochastic gradient descent, achieving a 4.1% improvement in RMSE for the Netflix dataset and an 1.8% for the Yahoo music dataset.

Multivariate categorical data occur in many applications of machine learning. One of the main difficulties with these vectors of categorical variables is sparsity. The number of possible observations grows exponentially with vector length, but dataset diversity might be poor in comparison. Recent models have gained significant improvement in supervised tasks with this data. These models embed observations in a continuous space to capture similarities between them. Building on these ideas we propose a Bayesian model for the unsupervised task of distribution estimation of multivariate categorical data. We model vectors of categorical variables as generated from a non-linear transformation of a continuous latent space. Non-linearity captures multi-modality in the distribution. The continuous representation addresses sparsity. Our model ties together many existing models, linking the linear categorical latent Gaussian model, the Gaussian process latent variable model, and Gaussian process classification. We derive inference for our model based on recent developments in sampling based variational inference. We show empirically that the model outperforms its linear and discrete counterparts in imputation tasks of sparse data.

Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Bayesian posterior inference could then, in principle, explain the observation. While intuitively appealing, generative models for computer vision have largely failed to deliver on that promise due to the difficulty of posterior inference. As a result the community has favoured efficient discriminative approaches. We still believe in the usefulness of generative models in computer vision, but argue that we need to leverage existing discriminative or even heuristic computer vision methods. We implement this idea in a principled way with an "informed sampler" and in careful experiments demonstrate it on challenging generative models which contain renderer programs as their components. We concentrate on the problem of inverting an existing graphics rendering engine, an approach that can be understood as "Inverse Graphics". The informed sampler, using simple discriminative proposals based on existing computer vision technology, achieves significant improvements of inference.

We provide a novel, flexible, iterative refinement algorithm to automatically construct an approximate statespace representation for Markov Decision Processes (MDPs). Our approach leverages bisimulation metrics, which have been used in prior work to generate features to represent the state space of MDPs. We address a drawback of this approach, which is the expensive computation of the bisimulation metrics. We propose an algorithm to generate an iteratively improving sequence of state space partitions. Partial metric computations guide the representation search and provide much lower space and computational complexity, while maintaining strong convergence properties. We provide theoretical results guaranteeing convergence as well as experimental illustrations of the accuracy and savings (in time and memory usage) of the new algorithm, compared to traditional bisimulation metric computation.

However, model calibration and the learning is critical for many prediction and decision-making of well-calibrated probabilistic models have not been tasks in artificial intelligence. In this paper we present a new studied in the machine learning literature as extensively as nonparametric calibration method called Bayesian Binning for example discriminative machine learning models that into Quantiles (BBQ) which addresses key limitations of existing are built to achieve the best possible discrimination among calibration methods. The method post processes the classes of objects. One way to achieve a high level of model output of a binary classification algorithm; thus, it can be calibration is to develop methods for learning probabilistic readily combined with many existing classification algorithms.

Applications of graphical models often require the use of approximate inference, such as sequential importance sampling (SIS), for estimation of the model distribution given partial evidence, i.e., the target distribution. However, when SIS proposal and target distributions are dissimilar, such procedures lead to biased estimates or require a prohibitive number of samples. We introduce ReBaSIS, a method that better approximates the target distribution by sampling variable by variable from existing importance samplers and accepting or rejecting each proposed assignment in the sequence: a choice made based on anticipating upcoming evidence. We relate the per-variable proposal and model distributions by expected weight ratios of sequence completions and show that we can learn accurate models of optimal acceptance probabilities from local samples. In a continuous-time domain, our method improves upon previous importance samplers by transforming an SIS problem into a machine learning one.

Combinatory Categorial Grammar (CCG) is a lexicalized grammar formalism in which words are associated with categories that, in combination with a small universal set of rules, specify the syntactic configurations in which they may occur. Categories are selected from a large, recursively-defined set; this leads to high word-to-category ambiguity, which is one of the primary factors that make learning CCG parsers difficult, especially in the face of little data. Previous work has shown that learning sequence models for CCG tagging can be improved by using linguistically-motivated prior probability distributions over potential categories. We extend this approach to the task of learning a CCG parser from weak supervision. We present a Bayesian formulation for CCG parser induction that assumes only supervision in the form of an incomplete tag dictionary mapping some word types to sets of potential categories. Our approach outperforms a baseline model trained with uniform priors by exploiting universal, intrinsic properties of the CCG formalism to bias the model toward simpler, more cross-linguistically common categories.

This paper describes a new information-theoretic policy evaluation technique for reinforcement learning. This technique converts any compression or density model into a corresponding estimate of value. Under appropriate stationarity and ergodicity conditions, we show that the use of a sufficiently powerful model gives rise to a consistent value function estimator. We also study the behavior of this technique when applied to various Atari 2600 video games, where the use of suboptimal modeling techniques is unavoidable. We consider three fundamentally different models, all too limited to perfectly model the dynamics of the system. Remarkably, we find that our technique provides sufficiently accurate value estimates for effective on-policy control. We conclude with a suggestive study highlighting the potential of our technique to scale to large problems.