HMC, an Algorithms in Data Mining, the Functional Analysis approach

Autor:	Ghosh, Soumyadip, Lu, Yingdong, Nowicki, Tomasz
Rok vydání:	2021
Předmět:	Statistics - Computation Computer Science - Machine Learning Mathematics - Dynamical Systems Mathematics - Functional Analysis 68W40 28A33 70H05 F.2
Druh dokumentu:	Working Paper
Popis:	The main purpose of this paper is to facilitate the communication between the Analytic, Probabilistic and Algorithmic communities. We present a proof of convergence of the Hamiltonian (Hybrid) Monte Carlo algorithm from the point of view of the Dynamical Systems, where the evolving objects are densities of probability distributions and the tool are derived from the Functional Analysis. Comment: arXiv admin note: text overlap with arXiv:2101.08688
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2102.02691 Zobrazit plný text záznamu View this record from Arxiv