Saved in:
Bibliographic Details
Main Authors: You, Haochen, Liu, Baojing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.01578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918152981446656
author You, Haochen
Liu, Baojing
author_facet You, Haochen
Liu, Baojing
contents Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation and Projection), a unified framework that generalizes clipping into smooth, per-layer gradient shaping. SPAMP tracks local gradient statistics, dynamically estimates thresholds, and applies power-based transformations to modulate update magnitudes in a differentiable manner. This perspective recasts clipping and warmup as dual mechanisms for controlling the effective update scale $η_t \|g_t\|$, offering a principled alternative to rigid heuristics. Extensive experiments across image and language tasks demonstrate that SPAMP improves stability, convergence, and robustness over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01578
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
You, Haochen
Liu, Baojing
Machine Learning
Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation and Projection), a unified framework that generalizes clipping into smooth, per-layer gradient shaping. SPAMP tracks local gradient statistics, dynamically estimates thresholds, and applies power-based transformations to modulate update magnitudes in a differentiable manner. This perspective recasts clipping and warmup as dual mechanisms for controlling the effective update scale $η_t \|g_t\|$, offering a principled alternative to rigid heuristics. Extensive experiments across image and language tasks demonstrate that SPAMP improves stability, convergence, and robustness over existing methods.
title Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
topic Machine Learning
url https://arxiv.org/abs/2510.01578