ExplorerData ScienceMachine Learning
Research PaperResearchia:202608.18005

Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run

Yunbum Kook

Abstract

For any convex body $\mathcal{K}\subset\mathbb{R}^{n}$ containing a unit ball, the spectral gap of Hit-and-Run is $Ω(1/(n^2 C_{\mathsf{PI}}))$, where $C_{\mathsf{PI}}$ is the Poincaré constant of the uniform distribution $π$ over $\mathcal{K}$. This implies that Hit-and-Run converges to a distribution within $χ^2$-divergence $\varepsilon$ of the uniform distribution $π$ in $O(n^2 C_{\mathsf{PI}}\log(M/\varepsilon))$ steps from any starting distribution $π_0$ with $M=χ^2(π_{0}\,\|\,π)$, thus refi...

Submitted: August 18, 2026Subjects: Machine Learning; Data Science

Description / Details

For any convex body KRn\mathcal{K}\subset\mathbb{R}^{n} containing a unit ball, the spectral gap of Hit-and-Run is Ω(1/(n2CPI))Ω(1/(n^2 C_{\mathsf{PI}})), where CPIC_{\mathsf{PI}} is the Poincaré constant of the uniform distribution ππ over K\mathcal{K}. This implies that Hit-and-Run converges to a distribution within χ2χ^2-divergence ε\varepsilon of the uniform distribution ππ in O(n2CPIlog(M/ε))O(n^2 C_{\mathsf{PI}}\log(M/\varepsilon)) steps from any starting distribution π0π_0 with M=χ2(π0π)M=χ^2(π_{0}\,\|\,π), thus refining the known bound of O(n2R2log(M/ε))O(n^2 R^2 \log(M/\varepsilon)) by Lovász and Vempala (2004) in terms of the outer radius RR; for nearly isotropic bodies, together with progress on the KLS conjecture, the complexity is O(n2lognlog(M/ε))O(n^2\log n\log(M/\varepsilon)), improving the dimension dependence from cubic to nearly quadratic while maintaining logarithmic dependence on the initial distance. It was an open problem to connect the convergence of Hit-and-Run to Poincaré/KLS constants as was done for the Ball walk by Kannan, Lovász and Simonovits (1997). Unlike Hit-and-Run, the Ball walk has an unavoidable linear dependence on (a stronger notion) of the initial warmness. We directly bound the spectral gap of the Hit-and-Run Markov chain by connecting it to functional isoperimetric constants, inspired by the recent analysis of In-and-Out. Rewriting the spectral gap in terms of dual certificates leads to the Babuška--Aziz constant studied in the analysis of PDEs; it is asymptotically bounded by the improved Poincaré constant, which we show can be bounded in terms of the usual Poincaré constant. The proof is based on duality and calculus, unlike known proofs of convergence for Hit-and-Run which are based on bounding the conductance. The same technique can be applied to Coordinate Hit-and-Run, resulting in a much improved mixing time of O(n3CPIlog(M/ε))O(n^3C_{\mathsf{PI}}\log(M/\varepsilon)).


Source: arXiv:2608.16878v1 - http://arxiv.org/abs/2608.16878v1 PDF: https://arxiv.org/pdf/2608.16878v1 Original Link: http://arxiv.org/abs/2608.16878v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Aug 18, 2026
Topic:
Data Science
Area:
Machine Learning
Comments:
0
Bookmark