HMC, an Algorithms in Data Mining, the Functional Analysis approach
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki

TL;DR
This paper introduces a functional analysis approach to prove the convergence of the Hamiltonian Monte Carlo algorithm, aiming to bridge analytic, probabilistic, and algorithmic communities in data mining.
Contribution
It provides a novel convergence proof of HMC using dynamical systems and functional analysis, enhancing theoretical understanding of the algorithm.
Findings
Proof of convergence of HMC from a dynamical systems perspective
Application of functional analysis to probabilistic density evolution
Bridging communities in data mining through theoretical insights
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Fault Detection and Control Systems · Statistical Methods and Inference
