In this paper, we present a hybrid grammar formalism designed to learn structured models of natural iconic gesture performances that allow for compressed representation and robust recognition. We analyze a dataset of iconic gestures and show how the proposed Feature-based Stochastic Context-Free Grammar (FSCFG) can generalize over both structural and feature-based variations among different gesture performances.

Exchangeability is a central notion in statistics and probability theory. The assumption that an infinite sequence of data points is exchangeable is at the core of Bayesian statistics. However, finite exchangeability as a statistical property that renders probabilistic inference tractable is less well-understood. We develop a theory of finite exchangeability and its relation to tractable probabilistic inference. The theory is complementary to that of independence and conditional independence. We show that tractable inference in probabilistic models with high treewidth and millions of variables can be explained with the notion of finite (partial) exchangeability. We also show that existing lifted inference algorithms implicitly utilize a combination of conditional independence and partial exchangeability.

Nowadays, most recommender systems (RSs) mainly aim to suggest appropriate items for individuals. Due to the social nature of human beings, group activities have become an integral part of our daily life, thus motivating the study on group RS (GRS). However, most existing methods used by GRS make recommendations through aggregating individual ratings or individual predictive results rather than considering the collective features that govern user choices made within a group. As a result, such methods are heavily sensitive to data, hence they often fail to learn group preferences when the data are slightly inconsistent with predefined aggregation assumptions. To this end, we devise a novel GRS approach which accommodates both individual choices and group decisions in a joint model. More specifically, we propose a deep-architecture model built with collective deep belief networks and dual-wing restricted Boltzmann machines. With such a deep model, we can use high-level features, which are induced from lower-level features, to represent group preference so as to relieve the vulnerability of data. Finally, the experiments conducted on a real-world dataset prove the superiority of our deep model over other state-of-the-art methods.

Maximization of submodular functions has wide applications in artificial intelligence and machine learning. In this paper, we propose a scalable learning algorithm for maximizing an adaptive submodular function. The key structural assumption in our solution is that the state of each item is distributed according to a generalized linear model, which is conditioned on the feature vector of the item. Our objective is to learn the parameters of this model. We analyze the performance of our algorithm, and show that its regret is polylogarithmic in time and linear in the number of features. Finally, we evaluate our solution on two problems, preference elicitation and adaptive face detection, and demonstrate that high-quality policies can be learned sample efficiently.

We formulate an approach to multiagent metareasoning that uses organizational design to focus each agent's reasoning on the aspects of its local problem that let it make the most worthwhile contributions to joint behavior. By employing the decentralized Markov decision process framework, we characterize an organizational design problem that explicitly considers the quantitative impact that a design has on both the quality of the agents' behaviors and their reasoning costs. We describe an automated organizational design process that can approximately solve our organizational design problem via incremental search, and present techniques that efficiently estimate the incremental impact of a candidate organizational influence. Our empirical evaluation confirms that our process generates organizational designs that impart a desired metareasoning regime upon the agents.

As a promising alternative to using standard (often intractable) planning techniques with Bellman equations, we propose an interesting method of optimizing POMDP controllers by probabilistic inference in a novel equivalent single-DBN generative model. Our inference approach to POMDP planning allows for (1) for application of various techniques for probabilistic inference in single graphical models, and (2) for exploiting the factored structure in a controller architecture to take advantage of natural structural constrains of planning problems and represent them compactly. Our contributions can be summarized as follows: (1) we designed a novel single-DBN generative model that ensures that the task of probabilistic inference is equivalent to the original problem of optimizing POMDP controllers, and (2) we developed several inference approaches to approximate the value of the policy when exact inference methods are not tractable to solve large-size problems with complex graphical models. The proposed approaches to policy optimization by probabilistic inference are evaluated on several POMDP benchmark problems and the performance of the implemented approximation algorithms is compared.

Qualitative Possibilistic Mixed-Observable MDPs (pi-MOMDPs), generalizing pi-MDPs and pi-POMDPs, are well-suited models to planning under uncertainty with mixed-observability when transition, observation and reward functions are not precisely known and can be qualitatively described. Functions defining the model as well as intermediate calculations are valued in a finite possibilistic scale L, which induces a finite belief state space under partial observability contrary to its probabilistic counterpart. In this paper, we propose the first study of factored pi-MOMDP models in order to solve large structured planning problems under qualitative uncertainty, or considered as qualitative approximations of probabilistic problems. Building upon the SPUDD algorithm for solving factored (probabilistic) MDPs, we conceived a symbolic algorithm named PPUDD for solving factored pi-MOMDPs. Whereas SPUDD's decision diagrams' leaves may be as large as the state space since their values are real numbers aggregated through additions and multiplications, PPUDD's ones always remain in the finite scale L via min and max operations only. Our experiments show that PPUDD's computation time is much lower than SPUDD, Symbolic-HSVI and APPL for possibilistic and probabilistic versions of the same benchmarks under either total or mixed observability, while still providing high-quality policies.

Restricted Boltzmann machines (RBMs) are a powerful generative modeling technique, based on a complex graphical model of hidden (latent) variables. Conditional RBMs (CRBMs) are an extension of RBMs tailored to modeling temporal data. A drawback of CRBMs is their consideration of linear temporal dependencies, which limits their capability to capture complex temporal structure. They also require many variables to model long temporal dependencies, a fact that might provoke overfitting proneness. To resolve these issues, in this paper we propose the echo-state CRBM (ES-CRBM): our model uses an echo-state network reservoir in the context of CRBMs to efficiently capture long and complex temporal dynamics, with much fewer trainable parameters compared to conventional CRBMs. In addition, we introduce an (implicit) mixture of ES-CRBM experts (im-ES-CRBM) to enhance even further the capabilities of our ES-CRBM model. The introduced im-ES-CRBM allows for better modeling temporal observations which might comprise a number of latent or observable subpatterns that alternate in a dynamic fashion. It also allows for performing sequence segmentation using our framework. We apply our methods to sequential data modeling and classification experiments using public datasets. As we show, our approach outperforms both existing RBM-based approaches as well as related state-of-the-art methods, such as conditional random fields.

Monte Carlo tree search (MCTS) algorithms are a popular approach to online decision-making in Markov decision processes (MDPs). These algorithms can, however, perform poorly in MDPs with high stochastic branching factors. In this paper, we study state aggregation as a way of reducing stochastic branching in tree search. Prior work has studied formal properties of MDP state aggregation in the context of dynamic programming and reinforcement learning, but little attention has been paid to state aggregation in MCTS. Our main result is a performance loss bound for a class of value function-based state aggregation criteria in expectimax search trees. We also consider how to construct MCTS algorithms that operate in the abstract state space but require a simulator of the ground dynamics only. We find that trajectory sampling algorithms like UCT can be adapted easily, but that sparse sampling algorithms present difficulties. As a proof of concept, we experimentally confirm that state aggregation can improve the finite-sample performance of UCT.

Recent advances of kernel methods have yielded a framework for representing probabilities using a reproducing kernel Hilbert space, called kernel embedding of distributions. In this paper, we propose a Monte Carlo filtering algorithm based on kernel embeddings. The proposed method is applied to state-space models where sampling from the transition model is possible, while the observation model is to be learned from training samples without assuming a parametric model. As a theoretical basis of the proposed method, we prove consistency of the Monte Carlo method combined with kernel embeddings. Experimental results on synthetic models and real vision-based robot localization confirm the effectiveness of the proposed approach.