Preprint
An Optimal First-Order Active-Hull Method for Convex Composite Hölder Smooth Optimization
arXiv
arXiv
11/07/2026
DOI: 10.48550/arxiv.2611.10916
Abstract
We consider the problem (P) : minx∈Rn f (x) + g(x) under the Euclidean geometry, where f is convex and (M, ν)-H¨older smooth on Rn, and g is proper, closed and convex on Rn, admits a generalized linear minimization oracle (GLMO), and has bounded domain with diameter D. An first-order active-hull (AH) method has access to both the first-order oracle (FO) of f and the GLMO of g, and outputs a point that lies in the convex hull of all the past GLMO returns. We propose a new first-order AH method for solving (P), which is based on our newly developed “recentered homotopy smoothing framework”. We show that in the high-dimensional regime, this method achieves the optimal FO and GLMO complexties simultaneously for all ν ∈ [0, 1].
Details
- Title: Subtitle
- An Optimal First-Order Active-Hull Method for Convex Composite Hölder Smooth Optimization
- Creators
- Renbo Zhao - University of Iowa
- Resource Type
- Preprint
- Publication Details
- arXiv
- DOI
- 10.48550/arxiv.2611.10916
- ISSN
- 2331-8422
- Publisher
- arXiv
- Language
- English
- Date posted
- 11/07/2026
- Academic Unit
- Business Analytics
- Record Identifier
- 9985253988402771
Metrics
1 Record Views