Skip to yearly menu bar Skip to main content


Poster

Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization

Sam Reifenstein · Timothee Leleu · Yoshihisa Yamamoto

Hall C 4-9 #2717
[ ] [ Project Page ] [ Paper PDF ]
[ Slides [ Poster
Tue 23 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

We propose a novel algorithm that extends the methods of ball smoothing and Gaussian smoothing for noisy derivative-free optimization by accounting for the heterogeneous curvature of the objective function. The algorithm dynamically adapts the shape of the smoothing kernel to approximate the Hessian of the objective function around a local optimum. This approach significantly reduces the error in estimating the gradient from noisy evaluations through sampling. We demonstrate the efficacy of our method through numerical experiments on artificial problems. Additionally, we show improved performance when tuning NP-hard combinatorial optimization solvers compared to existing state-ofthe-art heuristic derivative-free and Bayesian optimization methods.

Chat is not available.