Why Smooth Stability Assumptions Fail for ReLU Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Katende, Ronald
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915695016542208
author Katende, Ronald
author_facet Katende, Ronald
contents Stability analyses of modern learning systems are frequently derived under smoothness assumptions that are violated by ReLU-type nonlinearities. In this note, we isolate a minimal obstruction by showing that no uniform smoothness-based stability proxy such as gradient Lipschitzness or Hessian control can hold globally for ReLU networks, even in simple settings where training trajectories appear empirically stable. We give a concrete counterexample demonstrating the failure of classical stability bounds and identify a minimal generalized derivative condition under which stability statements can be meaningfully restored. The result clarifies why smooth approximations of ReLU can be misleading and motivates nonsmooth-aware stability frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Why Smooth Stability Assumptions Fail for ReLU Learning
Katende, Ronald
Machine Learning
Optimization and Control
Stability analyses of modern learning systems are frequently derived under smoothness assumptions that are violated by ReLU-type nonlinearities. In this note, we isolate a minimal obstruction by showing that no uniform smoothness-based stability proxy such as gradient Lipschitzness or Hessian control can hold globally for ReLU networks, even in simple settings where training trajectories appear empirically stable. We give a concrete counterexample demonstrating the failure of classical stability bounds and identify a minimal generalized derivative condition under which stability statements can be meaningfully restored. The result clarifies why smooth approximations of ReLU can be misleading and motivates nonsmooth-aware stability frameworks.
title Why Smooth Stability Assumptions Fail for ReLU Learning
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2512.22055