stat.MLNov 10, 2026

An Eyring-Kramers Formula for Singular Wells

Authors: Yingli Wang, Lingjiong Zhu

Organizations: School of Mathematical Sciences, Fudan University, Shanghai, People’s Republic of China · Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America

Abstract

Understanding the persistence of learned behaviors in AI safety motivates an investigation of the dynamical counterpart to the equilibrium geometry studied in singular learning theory. We analyze this persistence through transitions between singular wells. We establish an Eyring-Kramers formula for a low temperature Langevin diffusion between two compact connected zero components of a real-analytic potential. The wells may be singular and nonisolated, and the unique minimizing gate is a nondegenerate index-one saddle, with gates understood as inclusion-minimal sets meeting every minimizing path. A boundary-gate construction shows that uniqueness of this inclusion-minimal gate is equivalent to every minimizing path passing through the saddle and one such path meeting the communication level only there. Compact semianalytic topology provides a separating function away from a fixed saddle neighborhood; analytic Morse coordinates give matching capacity bounds by first sending the temperature to zero and then shrinking that neighborhood. An anchored energy estimate and a small-ball potential-theoretic identity give uniformity for deterministic starting points. The leading constant is expressed in terms of the sublevel-volume coefficient, a Gamma factor, and the saddle Hessian.

Explore similar work

CardsList
  1. Avoiding unsafe sets when training with Langevin Dynamics

    Jul 8, 2026Adam M. ObermanLangevin DynamicsStochastic Optimization Convergence

  2. Sharp dimensional analysis of midpoint methods for Langevin sampling

    Oct 5, 2026Fan Chen, Sinho Chewi, Jianfeng Lu +1Markov Chain Monte CarloStochastic Differential Equations