PreprintarXiv licencearXiv
On the Complexity of Finding Fixed Points for Set-Valued Contractions
Abstract
In this paper, we study the computational complexity of finding fixed points for set-valued contractions. We first formulate a computational problem for Nadler's fixed-point theorem: Projected-Nadler, and prove that it is CLS-complete by showing its equivalence to Continuous-LocalOpt. We then establish a stronger converse for Nadler's fixed point theorem that can be applied as a tool to analyze the convergence rate of set-valued basic iteration procedure. Finally, we reduce large-margin triplet stationarity problem to Projected-Nadler. Together with its CLS-hardness introduced in [arXiv:2509.16898], this yields CLS-completeness of large-margin triplet stationarity.
Related
- The Complexity of Finding Stationary Points in Nonsmooth Nonconvex Optimization
- On the Complexity of Finding Stationary Points of p-th Order Hölder Smooth Functions in One Dimension
- On the Complexity of Finding Stationary Points in Stochastic (L0, L1)-Smooth Nonconvex Optimization
- Fixed Point for Some Polynomial Contractions
- Finding New Limit Points of Mahler Measure by Methods of Missing Data Restoration
BibTeX
@misc{vlatakisgkaragkounis2026complexity,
title = {{On the Complexity of Finding Fixed Points for Set-Valued Contractions}},
author = {Emmanouil-Vasileios Vlatakis-Gkaragkounis and Pucheng Xiong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.14101},
eprint = {2609.14101},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.14101},
}
RIS
TY - UNPB
TI - On the Complexity of Finding Fixed Points for Set-Valued Contractions
AU - Emmanouil-Vasileios Vlatakis-Gkaragkounis
AU - Pucheng Xiong
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2609.14101
UR - https://arxiv.org/abs/2609.14101
AB - In this paper, we study the computational complexity of finding fixed points for set-valued contractions. We first formulate a computational problem for Nadler's fixed-point theorem: Projected-Nadler, and prove that it is CLS-complete by showing its equivalence to Continuous-LocalOpt. We then establish a stronger converse for Nadler's fixed point theorem that can be applied as a tool to analyze the convergence rate of set-valued basic iteration procedure. Finally, we reduce large-margin triplet stationarity problem to Projected-Nadler. Together with its CLS-hardness introduced in [arXiv:2509.16898], this yields CLS-completeness of large-margin triplet stationarity.
ER -