资源分类
》 资源 》论文》Positive Curvature and Hamiltonian Monte Carlo

Positive Curvature and Hamiltonian Monte Carlo

2020-01-19 | |  52 |   32 |   0

Abstract

The Jacobi metric introduced in mathematical physics can be used to analyze Hamiltonian Monte Carlo (HMC). In a geometrical setting, each step of HMC corresponds to a geodesic on a Riemannian manifold with a Jacobi metric. Our calculation of the sectional curvature of this HMC manifold allows us to see that it is positive in cases such as sampling from a high dimensional multivariate Gaussian. We show that positive curvature can be used to prove theoretical concentration results for HMC Markov chains.

上一篇：Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets

下一篇：Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...