Fixed Point Computation: Beating Brute Force with Smoothed Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Attias, Idan, Dagan, Yuval, Daskalakis, Constantinos, Yao, Rui, Zampetakis, Manolis
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910789683642368
author Attias, Idan
Dagan, Yuval
Daskalakis, Constantinos
Yao, Rui
Zampetakis, Manolis
author_facet Attias, Idan
Dagan, Yuval
Daskalakis, Constantinos
Yao, Rui
Zampetakis, Manolis
contents We propose a new algorithm that finds an $\varepsilon$-approximate fixed point of a smooth function from the $n$-dimensional $\ell_2$ unit ball to itself. We use the general framework of finding approximate solutions to a variational inequality, a problem that subsumes fixed point computation and the computation of a Nash Equilibrium. The algorithm's runtime is bounded by $e^{O(n)}/\varepsilon$, under the smoothed-analysis framework. This is the first known algorithm in such a generality whose runtime is faster than $(1/\varepsilon)^{O(n)}$, which is a time that suffices for an exhaustive search. We complement this result with a lower bound of $e^{Ω(n)}$ on the query complexity for finding an $O(1)$-approximate fixed point on the unit ball, which holds even in the smoothed-analysis model, yet without the assumption that the function is smooth. Existing lower bounds are only known for the hypercube, and adapting them to the ball does not give non-trivial results even for finding $O(1/\sqrt{n})$-approximate fixed points.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fixed Point Computation: Beating Brute Force with Smoothed Analysis
Attias, Idan
Dagan, Yuval
Daskalakis, Constantinos
Yao, Rui
Zampetakis, Manolis
Computer Science and Game Theory
Data Structures and Algorithms
Machine Learning
We propose a new algorithm that finds an $\varepsilon$-approximate fixed point of a smooth function from the $n$-dimensional $\ell_2$ unit ball to itself. We use the general framework of finding approximate solutions to a variational inequality, a problem that subsumes fixed point computation and the computation of a Nash Equilibrium. The algorithm's runtime is bounded by $e^{O(n)}/\varepsilon$, under the smoothed-analysis framework. This is the first known algorithm in such a generality whose runtime is faster than $(1/\varepsilon)^{O(n)}$, which is a time that suffices for an exhaustive search. We complement this result with a lower bound of $e^{Ω(n)}$ on the query complexity for finding an $O(1)$-approximate fixed point on the unit ball, which holds even in the smoothed-analysis model, yet without the assumption that the function is smooth. Existing lower bounds are only known for the hypercube, and adapting them to the ball does not give non-trivial results even for finding $O(1/\sqrt{n})$-approximate fixed points.
title Fixed Point Computation: Beating Brute Force with Smoothed Analysis
topic Computer Science and Game Theory
Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2501.10884