Saved in:
Bibliographic Details
Main Authors: Gal, Eshed, Fung, Samy Wu, Haber, Eldad
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13546
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918387826819072
author Gal, Eshed
Fung, Samy Wu
Haber, Eldad
author_facet Gal, Eshed
Fung, Samy Wu
Haber, Eldad
contents We introduce Probabilistic Gaussian Homotopy (PGH), a probability-space continuation framework for nonconvex optimization. Unlike classical Gaussian homotopy, which smooths the objective and uniformly averages gradients, PGH deforms the associated Boltzmann distribution and induces Boltzmann-weighted aggregation of perturbed gradients, which exponentially biases descent directions toward low-energy regions. We show that PGH corresponds to a log-sum-exp (soft-min) homotopy that smooths a nonconvex objective at scale $λ>0$ and recovers the original objective as $λ\to 0$, yielding a posterior-mean generalization of the Moreau envelope, and we derive a dynamical system governing minimizer evolution along an annealed homotopy path. This establishes a principled connection between Gaussian continuation, Bayesian denoising, and diffusion-style smoothing. We further propose Probabilistic Gaussian Homotopy Optimization (PGHO), a practical stochastic algorithm based on Monte Carlo gradient estimation, and demonstrate strong performance on high-dimensional nonconvex benchmarks and sparse recovery problems where classical gradient methods and objective-space smoothing frequently fail.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13546
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization
Gal, Eshed
Fung, Samy Wu
Haber, Eldad
Machine Learning
We introduce Probabilistic Gaussian Homotopy (PGH), a probability-space continuation framework for nonconvex optimization. Unlike classical Gaussian homotopy, which smooths the objective and uniformly averages gradients, PGH deforms the associated Boltzmann distribution and induces Boltzmann-weighted aggregation of perturbed gradients, which exponentially biases descent directions toward low-energy regions. We show that PGH corresponds to a log-sum-exp (soft-min) homotopy that smooths a nonconvex objective at scale $λ>0$ and recovers the original objective as $λ\to 0$, yielding a posterior-mean generalization of the Moreau envelope, and we derive a dynamical system governing minimizer evolution along an annealed homotopy path. This establishes a principled connection between Gaussian continuation, Bayesian denoising, and diffusion-style smoothing. We further propose Probabilistic Gaussian Homotopy Optimization (PGHO), a practical stochastic algorithm based on Monte Carlo gradient estimation, and demonstrate strong performance on high-dimensional nonconvex benchmarks and sparse recovery problems where classical gradient methods and objective-space smoothing frequently fail.
title Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization
topic Machine Learning
url https://arxiv.org/abs/2603.13546