# Power Homotopy for Zeroth-Order Non-Convex Optimizations

Source: [Power Homotopy for Zeroth-Order Non-Convex Optimizations](<https://www.sota2.com/research/paper/691bfe5b6750be83fe5cf101>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-17T05:00:05.621Z

Authors: Chen Xu

Published: 2025-11-17T16:54:30.000Z

## Abstract

The existing method of GS-PowerOpt solves the non-convex optimization problem of the form $\\max\_{\\boldsymbol{x} \\in \\mathbb{R}^d} f(\\boldsymbol{x})$ through maximizing a Gaussian-smoothed surrogate $F\_{N,\\sigma}(\\boldsymbol{\\mu}) = \\mathbb{E}\_{\\boldsymbol{x}\\sim\\mathcal{N}(\\boldsymbol{\\mu},\\sigma^2 I\_d)}\[e^{N f(\\boldsymbol{x})}\]$. We analyze the role of the smoothing radius $\\sigma\>0$ and identify a limitation of the fixed-$\\sigma$ design used in GS-PowerOpt. Specifically, $\\sigma$ induces an inherent exploration--refinement tradeoff: a larger $\\sigma$ improves global exploration and finite-time surrogate optimization, but may distort the location of the surrogate maximizer; in contrast, a smaller $\\sigma$ better preserves local structure but can weaken gradient signals away from high-value regions.   To address this limitation, we propose GS-PowerHP, a power-smoothed homotopy method with an incrementally decaying $\\sigma$ schedule. The proposed mechanism uses larger smoothing radii in early iterations to maintain informative gradient signals when the iterate is far from high-value regions, and gradually decreases $\\sigma$ to improve local refinement near the maximizer. We provide theoretical results showing that this decaying schedule improves the exploration--refinement tradeoff of fixed-$\\sigma$ power smoothing. Empirically, GS-PowerHP consistently outperforms the fixed-$\\sigma$ baseline and exhibits robust performance across different optimization tasks, including adversarial attacks on ImageNet ($d=150{,}528$), where it substantially improves over other smoothing-based zeroth-order methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.13592>)

[PDF](<https://arxiv.org/pdf/2511.13592.pdf>)
