This paper revisits the problem of learning a k-CNF Boolean function from examples, for fixed k, in the context of online learning under the logarithmic loss. We give a Bayesian interpretation to one of Valiant’s classic PAC learning algorithms, which we then build upon to derive three efficient, online, probabilistic, supervised learning algorithms for predicting the output of an unknown k-CNF Boolean function. We analyze the loss of our methods, and show that the cumulative log-loss can be upper bounded by a polynomial function of the size of each example.

Multi-label classification is a challenging and appealing supervised learning problem where a subset of labels, rather than a single label seen in traditional classification problems, is assigned to a single test instance. Classifier chains based methods are a promising strategy to tackle multi-label classification problems as they model label correlations at acceptable complexity. However, these methods are difficult to approximate the underlying dependency in the label space, and suffer from the problems of poorly ordered chain and error propagation. In this paper, we propose a novel polytree-augmented classifier chains method to remedy these problems. A polytree is used to model reasonable conditional dependence between labels over attributes, under which the directional relationship between labels within causal basins could be appropriately determined. In addition, based on the max-sum algorithm, exact inference would be performed on polytrees at reasonable cost, preventing from error propagation. The experiments performed on both artificial and benchmark multi-label data sets demonstrated that the proposed method is competitive with the state-of-the-art multi-label classification methods.

Gaussian processes (GPs) provide a nonparametric representation of functions. However, classical GP inference suffers from high computational cost for big data. In this paper, we propose a new Bayesian approach, EigenGP, that learns both basis dictionary elements — eigenfunctions of a GP prior — and prior precisions in a sparse finite model. It is well known that, among all orthogonal basis functions, eigenfunctions can provide the most compact representation. Unlike other sparse Bayesian finite models where the basis function has a fixed form, our eigenfunctions live in a reproducing kernel Hilbert space as a finite linear combination of kernel functions. We learn the dictionary elements — eigenfunctions — and the prior precisions over these elements as well as all the other hyperparameters from data by maximizing the model marginal likelihood. We explore computational linear algebra to simplify the gradient computation significantly. Our experimental results demonstrate improved predictive performance of EigenGP over alternative sparse GP methods as well as relevance vector machines.

In this paper, we study Bayesian techniques for entity discovery and temporal segmentation of videos. Existing temporal video segmentation techniques are based on low-level features, and are usually suitable for discovering short, homogeneous shots rather than diverse scenes, each of which contains several such shots. We define scenes in terms of semantic entities (eg. persons). This is the first attempt at entity-driven scene discovery in videos, without using meta-data like scripts. The problem is hard because we have no explicit prior information about the entities and the scenes. However such sequential data exhibit temporal coherence in multiple ways, and this provides implicit cues. To capture these, we propose a Bayesian generative model- EntScene, that represents entities with mixture components and scenes with discrete distributions over these components. The most challenging part of this approach is the inference, as it involves complex interactions of latent variables. To this end, we propose an algorithm based on Dynamic Blocked Gibbs Sampling, that attempts to jointly learn the components and the segmentation, by progressively merging an initial set of short segments. The proposed algorithm compares favourably against suitably designed baselines on several TV-series videos. We extend the method to an unexplored problem: temporal co-segmentation of videos containing same entities.

This paper studies active posterior estimation in a Bayesian setting when the likelihood is expensive to evaluate. Existing techniques for posterior estimation are based on generating samples representative of the posterior. Such methods do not consider efficiency in terms of likelihood evaluations. In order to be query efficient we treat posterior estimation in an active regression framework.  We propose two myopic query strategies to choose where to evaluate the likelihood and implement them using Gaussian processes. Via experiments on a series of synthetic and real examples we demonstrate that our approach is significantly more query efficient than existing techniques and other heuristics for posterior estimation.

A common way of attacking multi-label classification problems is by splitting it into a set of binary classification problems, then solving each problem independently using traditional single-label methods. Nevertheless, by learning classifiers separately the information about the relationship between labels tends to be neglected. Built on recent advances in structure learning in Ising Markov Random Fields (I-MRF), we propose a multi-label classification algorithm that explicitly estimate and incorporate label dependence into the classifiers learning process by means of a sparse convex multi-task learning formulation.Extensive experiments considering several existing multi-label algorithms indicate that the proposed method, while conceptually simple, outperforms the contenders in several datasets and performance metrics. Besides that, the conditional dependence graph encoded in the I-MRF provides a useful information that can be used in a posterior investigation regarding the reasons behind the relationship between labels.

Most multi-label domains lack an authoritative taxonomy. Therefore, different taxonomies are commonly used in the same domain, which results in complications. Although this situation occurs frequently, there has been little study of it using a principled statistical approach. Given that (1) different taxonomies used in the same domain are generally founded on the same latent semantic space, where each possible label set in a taxonomy denotes a single semantic concept, and that (2) crowdsourcing is beneficial in identifying relationships between semantic concepts and instances at low cost, we proposed a novel probabilistic cascaded method for establishing a semantic matching function in a crowdsourcing setting that maps label sets in one (source) taxonomy to label sets in another (target) taxonomy in terms of the semantic distances between them. The established function can be used to detect the associated label set in the target taxonomy for an instance directly from its associated label set in the source taxonomy without any extra effort. Experimental results on real-world data (emotion annotations for narrative sentences) demonstrated that the proposed method can robustly establish semantic matching functions exhibiting satisfactory performance from a limited number of crowdsourced annotations.

In practical applications, it is often observed that high-dimensional features can yield good performance, while being more costly in both computation and storage. In this paper, we propose a novel method called Bayesian Hashing to learn an optimal Hamming embedding of high-dimensional features, with a focus on the challenging application of face recognition. In particular, a boosted random FERNs classification model is designed to perform efficient face recognition, in which bit correlations are elaborately approximated with a random permutation technique. Without incurring additional storage cost, multiple random permutations are then employed to train a series of classifiers for achieving better discrimination power. In addition, we introduce a sequential forward floating search (SFFS) algorithm to perform model selection, resulting in further performance improvement. Extensive experimental evaluations and comparative studies clearly demonstrate that the proposed Bayesian Hashing approach outperforms other peer methods in both accuracy and speed. We achieve state-of-the-art results on well-known face recognition benchmarks using compact binary codes with significantly reduced computational overload and storage cost.

Count-based estimators are a fundamental building block of a number of powerful sequential prediction algorithms, including Context Tree Weighting and Prediction by Partial Matching. Keeping exact counts, however, typically results in a high memory overhead. In particular, when dealing with large alphabets the memory requirements of count-based estimators often become prohibitive. In this paper we propose three novel ideas for approximating count-based estimators using bounded memory. Our first contribution, of independent interest, is an extension of reservoir sampling for sampling distinct symbols from a stream of unknown length, which we call K-distinct reservoir sampling. We combine this sampling scheme with a state-of-the-art count-based estimator for memoryless sources, the Sparse Adaptive Dirichlet (SAD) estimator. The resulting algorithm, the Budget SAD, naturally guarantees a limit on its memory usage. We finally demonstrate the broader use of K-distinct reservoir sampling in nonparametric estimation by using it to restrict the branching factor of the Context Tree Weighting algorithm. We demonstrate the usefulness of our algorithms with empirical results on two sequential, large-alphabet prediction problems.

When a transition probability matrix is represented as the product of two stochastic matrices, swapping the factors of the multiplication yields another transition matrix that retains some fundamental characteristics of the original. Since the new matrix can be much smaller than its precursor, replacing the former for the latter can lead to significant savings in terms of computational effort. This strategy, dubbed the "stochastic-factorization trick," can be used to compute the stationary distribution of a Markov chain, to determine the fundamental matrix of an absorbing chain, and to compute a decision policy via dynamic programming or reinforcement learning. In this paper we show that the stochastic-factorization trick can also provide benefits in terms of the number of samples needed to estimate a transition matrix. We introduce a probabilistic interpretation of a stochastic factorization and build on the resulting model to develop an algorithm to compute the factorization directly from data. If the transition matrix can be well approximated by a low-order stochastic factorization, estimating its factors instead of the original matrix reduces significantly the number of parameters to be estimated. Thus, when compared to estimating the transition matrix directly via maximum likelihood, the proposed method is able to compute approximations of roughly the same quality using less data. We illustrate the effectiveness of the proposed algorithm by using it to help a reinforcement learning agent learn how to play the game of blackjack.