Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method
Abstract
We study approximations to the Moreau envelope---and infimal convolutions more broadly---based on Laplace's method, a classical tool in analysis which ties certain integrals to suprema of their integrands. We believe the connection between Laplace's method and infimal convolutions is generally deserving of more attention in the study of optimization and partial differential equations, since it bears numerous potentially important applications, from proximal-type algorithms to Hamilton-Jacobi equations.
Cite
Text
Tibshirani et al. "Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method." Journal of Machine Learning Research, 2025.Markdown
[Tibshirani et al. "Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method." Journal of Machine Learning Research, 2025.](https://mlanthology.org/jmlr/2025/tibshirani2025jmlr-laplace/)BibTeX
@article{tibshirani2025jmlr-laplace,
title = {{Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method}},
author = {Tibshirani, Ryan J. and Fung, Samy Wu and Heaton, Howard and Osher, Stanley},
journal = {Journal of Machine Learning Research},
year = {2025},
pages = {1-36},
volume = {26},
url = {https://mlanthology.org/jmlr/2025/tibshirani2025jmlr-laplace/}
}