mlsanityData to 14 Oct 2026

Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start

arXiv 2609.15884 ↗First posted 14 Sep 2026cs.DS cs.LG math.PRcited by 0

Not on the map. Why?

Abstract (arXiv)

We show that logconcave probability measures along the Gaussian cooling path have thin-shell stability, generalizing the thin-shell theorem. This result leads to improved complexity for the fundamental problem of sampling an arbitrary logconcave distribution from a cold start. For (near-)isotropic logconcave distributions, the complexity is nearly n2.5, improving the previous bound of n2.75, and matching the complexity of the abstract Speedy walk.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

11 of 33 references.

References · 11

  1. 2017Renyi Differential Privacycited by 650
  2. 2020Structured Logconcave Sampling with a Restricted Gaussian Oraclecited by 86
  3. 2024In-and-Out: Algorithmic Diffusion for Sampling Convex Bodiescited by 19
  4. 2024Sampling and Integration of Logconcave Functions by Algorithmic Diffusioncited by 12
  5. 2020Reducing Isotropy and Volume to KLS: Faster Rounding and Volume Algorithmscited by 9
  6. 2025Faster logconcave sampling from a cold start in high dimensioncited by 7
  7. 2025Zeroth-order Logconcave Samplingcited by 6
  8. 2014Gaussian Cooling and O*(n^3) Algorithms for Volume and Gaussian Volumecited by 5
  9. 2024R'enyi-infinity constrained sampling with d3 membership queriescited by 3
  10. 2026A unified complexity bound for logconcave samplingcited by 3
  11. 2026Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Runcited by 2

Built on by

Not cited yet.