22 : Hilbert Space Embeddings of Distributions Lecturer : Eric
نویسندگان
چکیده
The application of classical optimization techniques to Graphical Models has led to specialized derivations of powerful paradigms such as the class of EM algorithms, variational inference, max-margin and maximum entropy learning. This view has also sustained a conceptual bridge between the research communities of Graphical Models, Statistical Physics and Numerical Optimization. The optimization perspective has many advantages, based on a mature and diverse field that allows for problems to be easily formulated, efficiently solved, and approximated in a principled manner via convex relaxations. But it poses several challenges too, which are particularly limiting to problems that involve non-parametric continuous variables or non-convex objectives.
منابع مشابه
Hilbert Space Embeddings of POMDPs
A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes’ rule to these distribution embeddings. Policies and value functions are defin...
متن کاملMonte Carlo Filtering Using Kernel Embedding of Distributions
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 ...
متن کاملAlmost Bi-lipschitz Embeddings and Almost Homogeneous Sets
This paper is concerned with embeddings of homogeneous spaces into Euclidean spaces. We show that any homogeneous metric space can be embedded into a Hilbert space using an almost bi-Lipschitz mapping (biLipschitz to within logarithmic corrections). The image of this set is no longer homogeneous, but ‘almost homogeneous’. We therefore study the problem of embedding an almost homogeneous subset ...
متن کاملNonparametric Latent Tree Graphical Models: Inference, Estimation, and Structure Learning
Tree structured graphical models are powerful at expressing long range or hierarchical dependency among many variables, and have been widely applied in different areas of computer science and statistics. However, existing methods for parameter estimation, inference, and structure learning mainly rely on the Gaussian or discrete assumptions, which are restrictive under many applications. In this...
متن کاملNonparametric Tree Graphical Models via Kernel Embeddings
We introduce a nonparametric representation for graphical model on trees which expresses marginals as Hilbert space embeddings and conditionals as embedding operators. This formulation allows us to define a graphical model solely on the basis of the feature space representation of its variables. Thus, this nonparametric model can be applied to general domains where kernels are defined, handling...
متن کامل