Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sójka, Damian, Cygert, Sebastian, Masana, Marc
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908921706315776
author Sójka, Damian
Cygert, Sebastian
Masana, Marc
author_facet Sójka, Damian
Cygert, Sebastian
Masana, Marc
contents We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers. Existing derivative-free approaches struggle to balance runtime efficiency with learning capacity, as they either restrict updates to input prompts or require continuous, resource-intensive adaptation regardless of domain stability. To address these limitations, PACE leverages the Covariance Matrix Adaptation Evolution Strategy with the Fastfood projection to optimize high-dimensional affine parameters within a low-dimensional subspace, leading to superior adaptive performance. Furthermore, we enhance the runtime efficiency by incorporating an adaptation stopping criterion and a domain-specialized vector bank to eliminate redundant computation. Our framework achieves state-of-the-art accuracy across multiple benchmarks under continual distribution shifts, reducing runtime by over 50% compared to existing backpropagation-free methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28678
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
Sójka, Damian
Cygert, Sebastian
Masana, Marc
Machine Learning
We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers. Existing derivative-free approaches struggle to balance runtime efficiency with learning capacity, as they either restrict updates to input prompts or require continuous, resource-intensive adaptation regardless of domain stability. To address these limitations, PACE leverages the Covariance Matrix Adaptation Evolution Strategy with the Fastfood projection to optimize high-dimensional affine parameters within a low-dimensional subspace, leading to superior adaptive performance. Furthermore, we enhance the runtime efficiency by incorporating an adaptation stopping criterion and a domain-specialized vector bank to eliminate redundant computation. Our framework achieves state-of-the-art accuracy across multiple benchmarks under continual distribution shifts, reducing runtime by over 50% compared to existing backpropagation-free methods.
title Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
topic Machine Learning
url https://arxiv.org/abs/2603.28678