Convergence Analysis

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 33

All topics

Uniform-in-time convergence bounds for Persistent Contrastive Divergence algorithms
Oct 2, 2025Paul Felix Valsecchi Oliva, O. Deniz Akyildiz, Andrew DuncanParameter Estimation Stochastic Approximation
Department of Mathematics, Imperial College London
Towards Weaker Variance Assumptions for Stochastic Optimization
Apr 14, 2025Ahmet Alacaoglu, Yura Malitsky, Stephen J. WrightStochastic Optimization Last-Iterate Convergence
Department of Mathematics, University of British Columbia · Faculty of Mathematics, University of Vienna · Department of Computer Sciences, University of Wisconsin–Madison
Stability and Convergence of Optimistic Exponential Weights with Asymmetric Step Sizes in Bimatrix Games
Date pendingHédi Hadiji, Sarah SachsNash Equilibrium Last-Iterate Convergence
Laboratoire des Signaux et Systèmes, CentraleSupélec, Paris, France · School of Mathematics, University of Bristol, Bristol, United Kingdom

Oct 2, 2025, stat.MLJ/K move · Enter open · S save

Uniform-in-time convergence bounds for Persistent Contrastive Divergence algorithms

Paul Felix Valsecchi Oliva, O. Deniz Akyildiz, Andrew Duncan

Department of Mathematics, Imperial College London

Parameter Estimation Stochastic Approximation Energy-Based Models Convergence Analysis

Open paper AskPDF arXiv

We propose a continuous-time formulation of a noisy persistent contrastive divergence (PCD)-like method for maximum likelihood estimation (MLE) of unnormalised densities. Our approach couples parameter updates and sampling of the parametrised density in a multiscale system of stochastic differential equations (SDEs). From this formulation, we derive non-asymptotic bounds for weak test-function errors between the resulting numerical schemes and the MLE point target. The error is decomposed into numerical discretisation, slow-fast averaging, and finite-temperature concentration terms. We also introduce an efficient implementation based on explicit stabilized integrators and establish corresponding long-time error estimates. This leads to a novel method for training energy-based models (EBMs) with quantitative error guarantees.

Momentum

Related topics

Latest papers 33

Uniform-in-time convergence bounds for Persistent Contrastive Divergence algorithms

Towards Weaker Variance Assumptions for Stochastic Optimization

Stability and Convergence of Optimistic Exponential Weights with Asymmetric Step Sizes in Bimatrix Games