Saved in:
Bibliographic Details
Main Authors: Gao, Peifeng, Fang, Wenyi, Zheng, Yang, Zou, Difan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16809
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908975841148928
author Gao, Peifeng
Fang, Wenyi
Zheng, Yang
Zou, Difan
author_facet Gao, Peifeng
Fang, Wenyi
Zheng, Yang
Zou, Difan
contents Delayed loss spikes have been reported in neural-network training, but existing theory mainly explains earlier non-monotone behavior caused by overly large fixed learning rates. We study one stylized hypothesis: normalization can postpone instability by gradually increasing the effective learning rate during otherwise stable descent. To test this hypothesis at theorem level, we analyze batch-normalized linear models. Our flagship result concerns whitened square-loss linear regression, where we derive explicit no-rising-edge and delayed-onset conditions, bound the waiting time to directional onset, and show that the rising edge self-stabilizes within finitely many iterations. Combined with a square-loss decomposition, this yields a concrete delayed-spike mechanism in the whitened regime. For logistic regression, under highly restrictive active-margin assumptions, we prove only a supporting finite-horizon directional precursor in a knife-edge regime, with an optional appendix-only loss lower bound under an extra non-degeneracy condition. The paper should therefore be read as a stylized mechanism study rather than a general explanation of neural-network loss spikes. Within that scope, the results isolate one concrete delayed-instability pathway induced by batch normalization.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16809
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models
Gao, Peifeng
Fang, Wenyi
Zheng, Yang
Zou, Difan
Machine Learning
Optimization and Control
Delayed loss spikes have been reported in neural-network training, but existing theory mainly explains earlier non-monotone behavior caused by overly large fixed learning rates. We study one stylized hypothesis: normalization can postpone instability by gradually increasing the effective learning rate during otherwise stable descent. To test this hypothesis at theorem level, we analyze batch-normalized linear models. Our flagship result concerns whitened square-loss linear regression, where we derive explicit no-rising-edge and delayed-onset conditions, bound the waiting time to directional onset, and show that the rising edge self-stabilizes within finitely many iterations. Combined with a square-loss decomposition, this yields a concrete delayed-spike mechanism in the whitened regime. For logistic regression, under highly restrictive active-margin assumptions, we prove only a supporting finite-horizon directional precursor in a knife-edge regime, with an optional appendix-only loss lower bound under an extra non-degeneracy condition. The paper should therefore be read as a stylized mechanism study rather than a general explanation of neural-network loss spikes. Within that scope, the results isolate one concrete delayed-instability pathway induced by batch normalization.
title A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2604.16809