The Rao-Blackwell theorem is utilized to analyze and improve the scalability of inference in large probabilistic models that exhibit symmetries. A novel marginal density estimator is introduced and shown both analytically and empirically to outperform standard estimators by several orders of magnitude. The developed theory and algorithms apply to a broad class of probabilistic models including statistical relational models considered not susceptible to lifted probabilistic inference.

This paper proposes an effective approach to model the emotional space of words to infer their Sense Sentiment Similarity (SSS). SSS reflects the distance between the words regarding their senses and underlying sentiments. We propose a probabilistic approach that is built on a hidden emotional model in which the basic human emotions are considered as hidden. This leads to predict a vector of emotions for each sense of the words, and then to infer the sense sentiment similarity. The effectiveness of the proposed approach is investigated in two Natural Language Processing tasks: Indirect yes/no Question Answer Pairs Inference and Sentiment Orientation Prediction.

Anomaly detection for mixed-type data is an important problem that has not been well addressed in the machine learning field. There are two challenging issues for mixed-type datasets, namely modeling mutual correlations between mixed-type attributes and capturing large variations due to anomalies. This paper presents BuffDetect, a robust error buffering approach for anomaly detection in mixed-type datasets. A new variant of the generalized linear model is proposed to model the dependency between mixed-type attributes. The model incorporates an error buffering component based on Student-t distribution to absorb the variations caused by anomalies. However, because of the non- Gaussian design, the problem becomes analytically intractable. We propose a novel Bayesian inference approach, which integrates Laplace approximation and several computational optimizations, and is able to efficiently approximate the posterior of high dimensional latent variables by iteratively updating the latent variables in groups. Extensive experimental evaluations based on 13 benchmark datasets demonstrate the effectiveness and efficiency of BuffDetect.

Security games involving the allocation of multiple security resources to defend multiple targets generally have an exponential number of pure strategies for the defender. One method that has been successful in addressing this computational issue is to instead directly compute the marginal probabilities with which the individual resources are assigned (first pursued by Kiekintveld et al. (2009)). However, in sufficiently general settings, there exist games where these marginal solutions are not implementable, that is, they do not correspond to any mixed strategy of the defender. In this paper, we examine security games where the defender tries to monitor the vertices of a graph, and we show how the type of graph, the type of schedules, and the type of defender resources affect the applicability of this approach. In some settings, we show the approach is applicable and give a polynomial-time algorithm for computing an optimal defender strategy; in other settings, we give counterexample games that demonstrate that the approach does not work, and prove NP-hardness results for computing an optimal defender strategy.

One of the most widely studied classes of constraints in constraint programming (CP) is that of table constraints. Numerousspecialized filtering algorithms, enforcing the wellknown property called generalized arc consistency (GAC),have been developed for such constraints. Among the most successful GAC algorithms for table constraints, we find variants of simple tabular reduction (STR), like STR2. In this paper,we propose an extension of STR-based algorithms that achieves full pairwise consistency (FPWC), a consistency stronger than GAC and max restricted pairwise consistency (maxRPWC). Our approach involves counting the number of occurrences of specific combinations of values in constraint intersections. Importantly, the worst-case time complexity of one call to the basic filtering procedure at the heart of our new algorithm is quite close to that of STR algorithms. Experiments demonstrate that our method can outperform STR2 in many classes of problems, being significantly faster in some cases. Also, it is clearly superior to maxRPWC+, an algorithm that has been recently proposed.

This paper presents a novel framework for online incremental place recognition in an indoor environment. The framework addresses the scenario in which scene images are gradually obtained during long-term operation in the real-world indoor environment. Multiple users may interact with the classification system and confirm either current or past prediction results; the system then immediately updates itself to improve the classification system. This framework is based on the proposed \emph{n}-value self-organizing and incremental neural network (\emph{n}-SOINN), which has been derived by modifying the original SOINN to be appropriate for use in scene recognition. The evaluation was performed on the standard MIT 67-category indoor scene dataset and shows that the proposed framework achieves the same accuracy as that of the state-of-the-art offline method, while the computation time of the proposed framework is significantly faster and fully incremental update is allowed. Additionally, a small extra set of training samples is incrementally given to the system to simulate the incremental learning situation. The result shows that the proposed framework can leverage such additional samples and achieve the state-of-the-art result.

The tractability of a Constraint Satisfaction Problem (CSP)is guaranteed by a direct relationship between its consistencylevel and a structural parameter of its constraint network suchas the treewidth. This result is not widely exploited in practicebecause enforcing higher-level consistencies can be costlyand can change the structure of the constraint network andincrease its width. Recently, R(*,m)C was proposed as a relational consistency property that does not modify the structureof the graph and, thus, does not affect its width. In this paper,we explore two main strategies, based on a tree decomposition of the CSP, for improving the performance of enforcingR(*,m)C and getting closer to the above tractability condition. Those strategies are: a) localizing the application ofthe consistency algorithm to the clusters of the tree decomposition, and b) bolstering constraint propagation betweenclusters by adding redundant constraints at their separators,for which we propose three new schemes. We characterizethe resulting consistency properties by comparing them, theoretically and empirically, to the original R(*,m)C and thepopular GAC and maxRPWC, and establish the benefits ofour approach for solving difficult problems.

We study a simple sequential allocation mechanism for allocating indivisible goods between agents in which agents take turns to pick items.We focus on agents behaving strategically. We view the allocation procedure as a finite repeated game with perfect information. We show that with just two agents, we can compute the unique subgame perfect Nash equilibrium in linear time. With more agents, computing the subgame perfect Nash equilibria is more difficult. There can be an exponential number of equilibria and computing even one of them is PSPACE-hard. We identify a special case, when agents value many of the items identically, where we can efficiently compute the subgame perfect Nash equilibria. We also consider the effect of externalities and modifications to the mechanism that make it strategy proof.

Given a classification task, what is the best way to teach the resulting boundary to a human? While machine learning techniques can provide excellent methods for finding the boundary, including the selection of examples in an online setting, they tell us little about how we would teach a human the same task. We propose to investigate the problem of example selection and presentation in the context of teaching humans, and explore a variety of mechanisms in the interests of finding what may work best. In particular, we begin with the baseline of random presentation and then examine combinations of several mechanisms: the indication of an example’s relative difficulty, the use of the shaping heuristic from the cognitive science literature (moving from easier examples to harder ones), and a novel kernel-based “coverage model” of the subject’s mastery of the task. From our experiments on 54 human subjects learning and performing a pair of synthetic classification tasks via our teaching system, we found that we can achieve the greatest gains with a combination of shaping and the coverage model.

We study hybrid online-batch matching problems, where agents arrive continuously, but are only matched in periodic rounds, when many of them can be considered simultaneously. Agents not getting matched in a given round remain in the market for the next round. This setting models several scenarios of interest, including many job markets as well as kidney exchange mechanisms. We consider the social utility of two commonly used mechanisms for such markets: one that aims for stability in each round (greedy), and one that attempts to maximize social utility in each round (max-weight). Surprisingly, we find that in the long term, the social utility of the greedy mechanism can be higher than that of the max-weight mechanism. We hypothesize that this is because the greedy mechanism behaves similarly to a soft threshold mechanism, where all connections below a certain threshold are rejected by the participants in favor of waiting until the next round. Motivated by this observation, we propose a method to approximately calculate the optimal threshold for an individual agent to use based on characteristics of the other agents participating, and demonstrate experimentally that social utility is high when all agents use this strategy. Thresholding can also be applied by the mechanism itself to improve social welfare; we demonstrate this with an example on graphs that model pairwise kidney exchange.