Testing Approximate Stationarity Concepts for Piecewise Affine Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Lai, So, Anthony Man-Cho
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912178417696768
author Tian, Lai
So, Anthony Man-Cho
author_facet Tian, Lai
So, Anthony Man-Cho
contents We study the basic computational problem of detecting approximate stationary points for continuous piecewise affine (PA) functions. Our contributions span multiple aspects, including complexity, regularity, and algorithms. Specifically, we show that testing first-order approximate stationarity concepts, as defined by commonly used generalized subdifferentials, is computationally intractable unless P=NP. To facilitate computability, we consider a polynomial-time solvable relaxation by abusing the convex subdifferential sum rule and establish a tight characterization of its exactness. Furthermore, addressing an open issue motivated by the need to terminate the subgradient method in finite time, we introduce the first oracle-polynomial-time algorithm to detect so-called near-approximate stationary points for PA functions. A notable byproduct of our development in regularity is the first necessary and sufficient condition for the validity of an equality-type (Clarke) subdifferential sum rule. Our techniques revolve around two new geometric notions for convex polytopes and may be of independent interest in nonsmooth analysis. Moreover, some corollaries of our work on complexity and algorithms for stationarity testing address open questions in the literature. To demonstrate the versatility of our results, we complement our findings with applications to a series of structured piecewise smooth functions, including $ρ$-margin-loss SVM, piecewise affine regression, and nonsmooth neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03224
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Testing Approximate Stationarity Concepts for Piecewise Affine Functions
Tian, Lai
So, Anthony Man-Cho
Optimization and Control
We study the basic computational problem of detecting approximate stationary points for continuous piecewise affine (PA) functions. Our contributions span multiple aspects, including complexity, regularity, and algorithms. Specifically, we show that testing first-order approximate stationarity concepts, as defined by commonly used generalized subdifferentials, is computationally intractable unless P=NP. To facilitate computability, we consider a polynomial-time solvable relaxation by abusing the convex subdifferential sum rule and establish a tight characterization of its exactness. Furthermore, addressing an open issue motivated by the need to terminate the subgradient method in finite time, we introduce the first oracle-polynomial-time algorithm to detect so-called near-approximate stationary points for PA functions. A notable byproduct of our development in regularity is the first necessary and sufficient condition for the validity of an equality-type (Clarke) subdifferential sum rule. Our techniques revolve around two new geometric notions for convex polytopes and may be of independent interest in nonsmooth analysis. Moreover, some corollaries of our work on complexity and algorithms for stationarity testing address open questions in the literature. To demonstrate the versatility of our results, we complement our findings with applications to a series of structured piecewise smooth functions, including $ρ$-margin-loss SVM, piecewise affine regression, and nonsmooth neural networks.
title Testing Approximate Stationarity Concepts for Piecewise Affine Functions
topic Optimization and Control
url https://arxiv.org/abs/2501.03224