On quantitative Laplace-type convergence results for some exponential probability measures, with two applications

arXiv:2110.12922v2 Announce Type: replace-cross Abstract: Laplace-type results characterize the limit of sequence of measures (pi_arepsilon)_{arepsilon >0} with density w.r.t the Lebesgue measure (d pi_arepsilon / d Leb)(x) propto exp[-U(x)/arepsilon] when the temperature arepsilon>0 converges to 0. If a limiting distribution pi_0 exists, it concentrates on the minimizers of the potential U. Classical results require the invertibility of the Hessian of U in order to establish such asymptotics. In this work, we study the particular case of norm-like potentials U and establish quantitative bounds between pi_arepsilon and pi_0 w.r.t. the Wasserstein distance of order 1 under an invertibility condition of a generalized Jacobian. One key element of our proof is the use of geometric measure theory tools such as the coarea formula. We apply our results to the study of maximum entropy models (microcanonical/macrocanonical distributions) and to the convergence of the iterates of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm at low temperatures for non-convex minimization.

Related

• Sliced Wasserstein Steering between Gaussian Measures
• Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains
• Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis
• Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation

Source: arXiv cs.LG | 2026-04-29