יום ראשון, 4 באוקטובר 2026 LIVE
AI־INFO

כתבה arXiv cs.LG ·

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

Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
מאמר חדש: פיתוח שיטה לסימולציה של גופים ג'יבסיים עם פוטנציאלים לא-משותפים, עושה שימוש בתנאי תנועה עם תנע תמורה.
תקציר מקורי באנגליתarXiv:2610.02158v1 Announce Type: new 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, under these relaxed assumptions on the potential, the resulting dynamics leaves the target Gibbs measure invariant, and we establish exponential convergence to equilibrium in a weighted total variation distance. Finally, we show that the corresponding Euler-Maruyama discretization admits moment bounds that are uniform in time, without any modification
קרא במקור המקורי