Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation

arXiv:2603.28678 · cs.LG · Submitted 2026-03-30 · Read on arXiv

cs.LG

Submitted: 2026-03-30

Updated: 2026-09-06

Comments: Accepted to ECML PKDD 2026

Code: https://github.com/dmn-sjk/PACE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 103× in this paper · explained in 1 episode
• Accuracy — 39× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Domain Shift — 13× in this paper · explained in 4 episodes
• Distribution Shift — 7× in this paper · explained in 5 episodes
• Quantization — 6× in this paper · explained in 12 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Ablation Studies — 4× in this paper · explained in 1 episode
• Computational overhead — 4× in this paper · explained in 2 episodes
• Edge Devices — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Core — 3× in this paper · explained in 2 episodes
• Covariate Shift — 2× in this paper · explained in 2 episodes
• Domain Adaptation — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Fast Walsh-Hadamard Transform — 1× in this paper
• Kullback-Leibler (KL) Divergence — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Test-time Adaptation (TTA) — 1× in this paper · explained in 3 episodes

Sources

• The CMA Evolution Strategy: A Tutorial
• SITA: Single Image Test-time Adaptation
• TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
• ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
• DELTA: degradation-free fully test-time adaptation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks