SAFE: Finding Sparse and Flat Minima to Improve Pruning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Dongyeop, Lee, Kwanhee, Chung, Jinseok, Lee, Namhoon
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913895059292160
author Lee, Dongyeop
Lee, Kwanhee
Chung, Jinseok
Lee, Namhoon
author_facet Lee, Dongyeop
Lee, Kwanhee
Chung, Jinseok
Lee, Namhoon
contents Sparsifying neural networks often suffers from seemingly inevitable performance degradation, and it remains challenging to restore the original performance despite much recent progress. Motivated by recent studies in robust optimization, we aim to tackle this problem by finding subnetworks that are both sparse and flat at the same time. Specifically, we formulate pruning as a sparsity-constrained optimization problem where flatness is encouraged as an objective. We solve it explicitly via an augmented Lagrange dual approach and extend it further by proposing a generalized projection operation, resulting in novel pruning methods called SAFE and its extension, SAFE$^+$. Extensive evaluations on standard image classification and language modeling tasks reveal that SAFE consistently yields sparse networks with improved generalization performance, which compares competitively to well-established baselines. In addition, SAFE demonstrates resilience to noisy data, making it well-suited for real-world conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06866
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAFE: Finding Sparse and Flat Minima to Improve Pruning
Lee, Dongyeop
Lee, Kwanhee
Chung, Jinseok
Lee, Namhoon
Machine Learning
Artificial Intelligence
Sparsifying neural networks often suffers from seemingly inevitable performance degradation, and it remains challenging to restore the original performance despite much recent progress. Motivated by recent studies in robust optimization, we aim to tackle this problem by finding subnetworks that are both sparse and flat at the same time. Specifically, we formulate pruning as a sparsity-constrained optimization problem where flatness is encouraged as an objective. We solve it explicitly via an augmented Lagrange dual approach and extend it further by proposing a generalized projection operation, resulting in novel pruning methods called SAFE and its extension, SAFE$^+$. Extensive evaluations on standard image classification and language modeling tasks reveal that SAFE consistently yields sparse networks with improved generalization performance, which compares competitively to well-established baselines. In addition, SAFE demonstrates resilience to noisy data, making it well-suited for real-world conditions.
title SAFE: Finding Sparse and Flat Minima to Improve Pruning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.06866