Convex optimization with $p$-norm oracles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adil, Deeksha, Bullins, Brian, Jambulapati, Arun, Sidford, Aaron
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912825633406976
author Adil, Deeksha
Bullins, Brian
Jambulapati, Arun
Sidford, Aaron
author_facet Adil, Deeksha
Bullins, Brian
Jambulapati, Arun
Sidford, Aaron
contents In recent years, there have been significant advances in efficiently solving $\ell_s$-regression using linear system solvers and $\ell_2$-regression [Adil-Kyng-Peng-Sachdeva, J. ACM'24]. Would efficient smoothed $\ell_p$-norm solvers lead to even faster rates for solving $\ell_s$-regression when $2 \leq p < s$? In this paper, we give an affirmative answer to this question and show how to solve $\ell_s$-regression using $\tilde{O}(n^{\fracν{1+ν}})$ iterations of solving smoothed $\ell_p$ regression problems, where $ν:= \frac{1}{p} - \frac{1}{s}$. To obtain this result, we provide improved accelerated rates for convex optimization problems when given access to an $\ell_p^s(λ)$-proximal oracle, which, for a point $c$, returns the solution of the regularized problem $\min_{x} f(x) + λ||x-c||_p^s$. Additionally, we show that these rates for the $\ell_p^s(λ)$-proximal oracle are optimal for algorithms that query in the span of the outputs of the oracle, and we further apply our techniques to settings of high-order and quasi-self-concordant optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2410_24158
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convex optimization with $p$-norm oracles
Adil, Deeksha
Bullins, Brian
Jambulapati, Arun
Sidford, Aaron
Optimization and Control
Data Structures and Algorithms
In recent years, there have been significant advances in efficiently solving $\ell_s$-regression using linear system solvers and $\ell_2$-regression [Adil-Kyng-Peng-Sachdeva, J. ACM'24]. Would efficient smoothed $\ell_p$-norm solvers lead to even faster rates for solving $\ell_s$-regression when $2 \leq p < s$? In this paper, we give an affirmative answer to this question and show how to solve $\ell_s$-regression using $\tilde{O}(n^{\fracν{1+ν}})$ iterations of solving smoothed $\ell_p$ regression problems, where $ν:= \frac{1}{p} - \frac{1}{s}$. To obtain this result, we provide improved accelerated rates for convex optimization problems when given access to an $\ell_p^s(λ)$-proximal oracle, which, for a point $c$, returns the solution of the regularized problem $\min_{x} f(x) + λ||x-c||_p^s$. Additionally, we show that these rates for the $\ell_p^s(λ)$-proximal oracle are optimal for algorithms that query in the span of the outputs of the oracle, and we further apply our techniques to settings of high-order and quasi-self-concordant optimization.
title Convex optimization with $p$-norm oracles
topic Optimization and Control
Data Structures and Algorithms
url https://arxiv.org/abs/2410.24158