Interruptible pure exploration in multi-armed bandits (MABs) is a key component of Monte-Carlo tree search algorithms for sequential decision problems. We introduce Discriminative Bucketing (DB), a novel family of strategies for pure exploration in MABs, which allows for adapting recent advances in non-interruptible strategies to the interruptible setting, while guaranteeing exponential-rate performance improvement over time. Our experimental evaluation demonstrates that the corresponding instances of DB favorably compete both with the currently popular strategies UCB1 and Epsilon-Greedy, as well as with the conservative uniform sampling.

We examine the inferential complexity of Bayesian networks specified through logical constructs. We first consider simple propositional languages, and then move to relational languages. We examine both the combined complexity of inference (as network size and evidence size are not bounded) and the data complexity of inference (where network size is bounded); we also examine the connection to liftability through domain complexity. Combined and data complexity of several inference problems are presented, ranging from polynomial to exponential classes.

Sequential decision problems that involve multiple objectives are prevalent. Consider for example a driver of a semi-autonomous car who may want to optimize competing objectives such as travel time and the effort associated with manual driving. We introduce a rich model called Lexicographic MDP (LMDP) and a corresponding planning algorithm called LVI that generalize previous work by allowing for conditional lexicographic preferences with slack. We analyze the convergence characteristics of LVI and establish its game theoretic properties. The performance of LVI in practice is tested within a realistic benchmark problem in the domain of semi-autonomous driving. Finally, we demonstrate how GPU-based optimization can improve the scalability of LVI and other value iteration algorithms for MDPs.

The problem of planning or discrete control for timed system has earlier been solved with various constraint-based solution methods, including Constraint Programming, SAT solvers, SAT modulo Theories solvers, and Mixed Integer-Linear Programming. In this work we investigate the encoding of time in such constraint-based representations. A main issue with existing encodings is the necessity to allow arbitrary interleavings of concurrent actions' starting and ending times. The complex combinatorics of this can lead to poor scalability of leading search methods. We show how real or rational time in temporal models can in many practically important cases be replaced by integer time, and how this leads to far simpler encodings of planning as constraints. We demonstrate that the simplified encodings substantially improve the scalability of constraint-based planning.

The classical planning problem can be enriched with quantitative and qualitative user-defined preferences on how the system behaves on achieving the goal. In this paper, we propose the probabilistic preference planning problem for Markov decision processes, where the preferences are based on an enriched probabilistic LTL-style logic. We develop P4Solver, an SMT-based planner computing the preferred plan by reducing the problem to quadratic programming problem, which can be solved using SMT solvers such as Z3. We illustrate the framework by applying our approach on two selected case studies.

We present a probabilistic framework for learning pairwise similarities between objects belonging to different modalities, such as drugs and proteins, or text and images. Our framework is based on learning a binary code based representation for objects in each modality, and has the following key properties: (i) it can leverage both pairwise as well as easy-to-obtain relative preference based cross-modal constraints, (ii) the probabilistic framework naturally allows querying for the most useful/informative constraints, facilitating an active learning setting (existing methods for cross-modal similarity learning do not have such a mechanism), and (iii) the binary code length is learned from the data. We demonstrate the effectiveness of the proposed approach on two problems that require computing pairwise similarities between cross-modal object pairs: cross-modal link prediction in bipartite graphs, and hashing based cross-modal similarity search.

This paper is concerned with the problem of domain adaptation with multiple sources from a causal point of view. In particular, we use causal models to represent the relationship between the features X and class label Y , and consider possible situations where different modules of the causal model change with the domain. In each situation, we investigate what knowledge is appropriate to transfer and find the optimal target-domain hypothesis. This gives an intuitive interpretation of the assumptions underlying certain previous methods and motivates new ones. We finally focus on the case where Y is the cause for X with changing PY and PX|Y , that is, PY and PX|Y change independently across domains. Under appropriate assumptions, the availability of multiple source domains allows a natural way to reconstruct the conditional distribution on the target domain; we propose to model PX|Y (the process to generate effect X from cause Y ) on the target domain as a linear mixture of those on source domains, and estimate all involved parameters by matching the target-domain feature distribution. Experimental results on both synthetic and real-world data verify our theoretical results.

Naive Bayes (NB) is well-known to be a simple but effective classifier, especially when combined with feature selection. Unfortunately, feature selection methods are often greedy and thus cannot guarantee an optimal feature set is selected. An alternative to feature selection is to use Bayesian model averaging (BMA), which computes a weighted average over multiple predictors; when the different predictor models correspond to different feature sets, BMA has the advantage over feature selection that its predictions tend to have lower variance on average in comparison to any single model. In this paper, we show for the first time that it is possible to exactly evaluate BMA over the exponentially-sized powerset of NB feature models in linear-time in the number of features; this yields an algorithm about as expensive to train as a single NB model with all features, but yet provably converges to the globally optimal feature subset in the asymptotic limit of data. We evaluate this novel BMA-NB classifier on a range of datasets showing that it never underperforms NB (as expected) and sometimes offers performance competitive (or superior) to classifiers such as SVMs and logistic regression while taking a fraction of the time to train.

Learning for maximizing AUC performance is an important research problem in machine learning. Unlike traditional batch learning methods for maximizing AUC which often suffer from poor scalability, recent years have witnessed some emerging studies that attempt to maximize AUC by single-pass online learning approaches. Despite their encouraging results reported, the existing online AUC maximization algorithms often adopt simple stochastic gradient descent approaches, which fail to exploit the geometry knowledge of the data observed in the online learning process, and thus could suffer from relatively slow convergence. To overcome the limitation of the existing studies, in this paper, we propose a novel algorithm of Adaptive Online AUC Maximization (AdaOAM), by applying an adaptive gradient method for exploiting the knowledge of historical gradients to perform more informative online learning. The new adaptive updating strategy by AdaOAM is less sensitive to parameter settings due to its natural effect of tuning the learning rate. In addition, the time complexity of the new algorithm remains the same as the previous non-adaptive algorithms. To demonstrate the effectiveness of the proposed algorithm, we analyze its theoretical bound, and further evaluate its empirical performance on both public benchmark datasets and anomaly detection datasets. The encouraging empirical results clearly show the effectiveness and efficiency of the proposed algorithm.

Social media platforms are often used by people to express their needs and desires. Such data offer great opportunities to identify users’ consumption intention from user-generated contents, so that better tailored products or services can be recommended. However, there have been few efforts on mining commercial intents from social media contents. In this paper, we investigate the use of social media data to identify consumption intentions for individuals. We develop a Consumption Intention Mining Model (CIMM) based on convolutional neural network (CNN), for identifying whether the user has a consumption intention. The task is domain-dependent, and learning CNN requires a large number of annotated instances, which can be available only in some domains. Hence, we investigate the possibility of transferring the CNN mid-level sentence representation learned from one domain to another by adding an adaptation layer. To demonstrate the effectiveness of CIMM, we conduct experiments on two domains. Our results show that CIMM offers a powerful paradigm for effectively identifying users’ consumption intention based on their social media data. Moreover, our results also confirm that the CNN learned in one domain can be effectively transferred to another domain. This suggests that a great potential for our model to significantly increase effectiveness of product recommendations and targeted advertising.