We present a novel approach for multilabel classification based on an ensemble of Bayesian networks. The class variables are connected by a tree; each model of the ensemble uses a different class as root of the tree. We assume the features to be conditionally independent given the classes, thus generalizing the naive Bayes assumption to the multiclass case. This assumption allows us to optimally identify the correlations between classes and features; such correlations are moreover shared across all models of the ensemble. Inferences are drawn from the ensemble via logarithmic opinion pooling. To minimize Hamming loss, we compute the marginal probability of the classes by running standard inference on each Bayesian network in the ensemble, and then pooling the inferences. To instead minimize the subset 0/1 loss, we pool the joint distributions of each model and cast the problem as a MAP inference in the corresponding graphical model. Experiments show that the approach is competitive with state-of-the-art methods for multilabel classification.

Relational topic models have shown promise on analyzing document network structures and discovering latent topic representations. This paper presents three extensions: 1) unlike the common link likelihood with a diagonal weight matrix that allows the-same-topic interactions only, we generalize it to use a full weight matrix that captures all pairwise topic interactions and is applicable to asymmetric networks; 2) instead of doing standard Bayesian inference, we perform regularized Bayesian inference with a regularization parameter to deal with the imbalanced link structure issue in common real networks; and 3) instead of doing variational approximation with strict mean-field assumptions, we present a collapsed Gibbs sampling algorithm for the generalized relational topic models without making restricting assumptions. Experimental results demonstrate the significance of these extensions on improving the prediction performance, and the time efficiency can be dramatically improved with a simple fast approximation method.

We target the problem of accuracy and robustness in causal inference from finite data sets. Our aim is to combine the inherent robustness of the Bayesian approach with the theoretical strength and clarity of constraint-based methods. We use a Bayesian score to obtain probability estimates on the input statements used in a constraint-based procedure. These are subsequently processed in decreasing order of reliability, letting more reliable decisions take precedence in case of conflicts, until a single output model is obtained. Tests show that a basic implementation of the resulting Bayesian Constraint-based Causal Discovery (BCCD) algorithm already outperforms established procedures such as FCI and Conservative PC. It indicates which causal decisions in the output have high reliability and which do not. The approach is easily adapted to other application areas such as complex independence tests.

Decision theory focuses on the problem of making decisions under uncertainty. This uncertainty arises from the unknown aspects of the state of the world the decision maker is in or the unknown utility function of performing actions. The uncertainty can be modeled as a probability distribution capturing our belief about the world the decision maker is in. Upon making new observations, the decision maker becomes more confident about this model. In addition, if there is a prior belief on this uncertainty that may have obtained from similar experiments, the Bayesian methods may be employed. The loss incurred by the decision maker can also be utilized for the optimal action selection. Most machine learning algorithms developed though focus on one of these aspects for learning and prediction; either learning the probabilistic model or minimizing the loss. In probabilistic models, approximate inference, the process of obtaining the desired model from the observations when its is not tractable, does not consider the task loss. On the other end of the spectrum, the common practice in learning is to minimize the task loss without considering the uncertainty of prediction model. Therefore, we investigate the intersection of decision theory and machine learning considering both uncertainty in prediction model and the task loss.

We present a reformulation of the stochastic optimal control problem in terms of KL divergence minimisation, not only providing a unifying perspective of previous approaches in this area, but also demonstrating that the formalism leads to novel practical approaches to the control problem. Specifically, a natural relaxation of the dual formulation gives rise to exact iterative solutions to the finite and infinite horizon stochastic optimal control problem, while direct application of Bayesian inference methods yields instances of risk sensitive control.

Thresholding a measure in conditional independence (CI) tests using a fixed value enables learning and removing edges as part of learning a Bayesian network structure. However, the learned structure is sensitive to the threshold that is commonly selected: 1) arbitrarily; 2) irrespective of characteristics of the domain; and 3) fixed for all CI tests. We analyze the impact on mutual information – a CI measure – of factors, such as sample size, degree of variable dependence, and variables’ cardinalities. Following, we suggest to adaptively threshold individual tests based on the factors. We show that adaptive thresholds better distinguish between pairs of dependent variables and pairs of independent variables and enable learning structures more accurately and quickly than when using fixed thresholds.

Security is a critical concern around the world. Since resources for security are always limited, lots of interest have arisen in using game theory to handle security resource allocation problems. However, most of the existing work does not address adequately how a defender chooses his optimal strategy in a game with absent, inaccurate, uncertain, and even ambiguous strategy profiles' payoffs. To address this issue, we propose a general framework of security games under ambiguities based on Dempster-Shafer theory and the ambiguity aversion principle of minimax regret. Then, we reveal some properties of this framework. Also, we present two methods to reduce the influence of complete ignorance. Our investigation shows that this new framework is better in handling security resource allocation problems under ambiguities.

A fault represents some erroneous operation of a system that could result from an action selection error or some abnormal condition. We formally define error models that characterize the likelihood of various faults and consider the problem of fault-tolerant planning, which optimizes performance given an error model. We show that factoring the possibility of errors significantly degrades the performance of stochastic planning algorithms such as LAO*, because the number of reachable states grows dramatically. We introduce an approach to plan for a bounded number of faults and analyze its theoretical properties. When combined with a continual planning paradigm, the k-fault-tolerant planning method can produce near-optimal performance, even when the number of faults exceeds the bound. Empirical results in two challenging domains confirm the effectiveness of the approach in handling different types of runtime errors.

We present a new sampling approach to Bayesian learning of the Bayesian network structure. Like some earlier sampling methods, we sample linear orders on nodes rather than directed acyclic graphs (DAGs). The key difference is that we replace the usual Markov chain Monte Carlo (MCMC) method by the method of annealed importance sampling (AIS). We show that AIS is not only competitive to MCMC in exploring the posterior, but also superior to MCMC in two ways: it enables easy and efficient parallelization, due to the independence of the samples, and lower-bounding of the marginal likelihood of the model with good probabilistic guarantees. We also provide a principled way to correct the bias due to order-based sampling, by implementing a fast algorithm for counting the linear extensions of a given partial order.

Mobile manipulation robots are envisioned to provide many useful services both in domestic environments as well as in the industrial context.  In this paper, we present novel approaches to allow mobile maniplation systems to autonomously adapt to new or changing situations. The approaches developed in this paper cover the following four topics: (1) learning the robot's kinematic structure and properties using actuation and visual feedback, (2) learning about articulated objects in the environment in which the robot is operating, (3) using tactile feedback to augment visual perception, and (4) learning novel manipulation tasks from human demonstrations.