Year: 2024
Type: article
Abstract: We propose a randomized multiplicative weight update (MWU) algorithm for 𝓁_{∞} regression that runs in Õ(n^{2+1/22.5} poly(1/ε)) time when ω = 2+o(1), improving upon the previous best Õ(n^{2+1/18} polylog(1/ε)) runtime in the low-accuracy regime. Our algorithm combines state-of-the-art inverse maintenance data structures with acceleration. In order to do so, we propose a novel acceleration scheme for MWU that exhibits stability and robustness, which are required for the efficient implementations of the inverse maintenance data structures. We also design a faster deterministic MWU algorithm that runs in Õ(n^{2+1/12}poly(1/ε)) time when ω = 2+o(1), improving upon the previous best Õ(n^{2+1/6} poly log(1/ε)) runtime in the low-accuracy regime. We achieve this by showing a novel stability result that goes beyond previously known works based on interior point methods (IPMs). Our work is the first to use acceleration and inverse maintenance together efficiently, finally making the two most important building blocks of modern structured convex optimization compatible.
Parent work: LIPIcs, Volume 334, ICALP 2025, Complete Volume
Authors: Adil, Deeksha, Jiang, Shunhua, Kyng, Rasmus
Institutions: ETH Zurich, Columbia University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: AF:Small: Nearest Neighbor Search in High Dimensional Spaces, TRIPODS: From Foundations to Practice of Data Science and Back, Algorithms and complexity for high-accuracy flows and convex optimization, AF:Small: Data-Dependent Algorithms for High-Dimensional Data, G6671297155, CAREER: Information Theoretic Methods in Data Structures, G993971353
OpenAlex ID: W7109952141
