Signals 4 · free daily AI digest

Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials

Paper recorded by Signals 4 on 2026-10-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-01 on arXiv · recorded by Signals 4 on 2026-10-02

Category: cs.LG · 机器学习 · first seen 2026-10-02

Abstract

We consider the problem of sampling from Gibbs distributions on matrix spaces whose potential energies are neither convex nor globally gradient-Lipschitz. We introduce a family of non-quadratic kinetic energies that lead to a new underdamped Langevin system with momentum preconditioning, in which the gradient of the kinetic energy acts as a smooth spectral taming of the momentum. We prove that, un

Read on arXiv →

#12 most recent of 362 cs.LG papers we have recorded · ↑ newer: When Do Intrinsic Rewards Lead to Exploration? · ↓ older: Faynt: Scaling and Optimizing Policies for Competitive Melee
Cite this page: Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials: the #12 most recent of 362 cs.LG papers we have recorded (as of 2026-10-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/muon-meets-tamed-langevin-momentum-preconditioning-beyond-convex-and-gradient-li.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