Signals 4 · free daily AI digest

On two proofs of $d^2$ mixing of weighted Dikin walks

Paper recorded by Signals 4 on 2026-08-28 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.LG · 机器学习 · first seen 2026-08-31

Abstract

We study the mixing time of weighted Dikin walks for sampling from exponential distributions on polytopes and truncated positive-semidefinite (PSD) cones. Our first result gives a general total-variation mixing bound under strong self-concordance, $\barν$-symmetry, and mixed-trace regularity on the local metric. The key idea is to control the Metropolis--Hastings acceptance probability on a high-p

Read on arXiv →

#202 most recent of 215 cs.LG papers we have recorded · ↑ newer: QGPINNs: A Physics-Informed Neural Network Framework for Nonlocal Diff · ↓ older: Learning between the peaks: sharp asymptotics for kernel ridge regress
Cite this page: On two proofs of $d^2$ mixing of weighted Dikin walks: the #202 most recent of 215 cs.LG papers we have recorded (as of 2026-08-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/on-two-proofs-of-d-2-mixing-of-weighted-dikin-walks.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions