Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation

• URL: http://arxiv.org/abs/2603.28678v1
• Date: Mon, 30 Mar 2026 16:58:13 GMT
• Title: Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
• Abstract summary: PACE is a backpropagation-free continual test-time adaptation system.<n>It directly optimize the affine parameters of normalization layers.<n>Our framework achieves state-of-the-art accuracy across multiple benchmarks under continual distribution shifts.
• Score: 8.1094804369744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• Deep Learning-Accelerated Surrogate Optimization for High-Dimensional Well Control in Stress-Sensitive Reservoirs [0.0]
  Production optimization in stress-sensitive unconventional reservoirs is governed by a nonlinear trade-off between pressure-driven flow and stress-induced degradation of fracture conductivity and matrix permeability.<n>We propose a deep learning-based surrogate optimization framework for high-dimensional well control.
  arXiv  Detail & Related papers  (2026-04-01T01:04:08Z)
• The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation [86.83038620308423]
  Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data.<n>We propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP.
  arXiv  Detail & Related papers  (2026-03-23T12:48:38Z)
• JAWS: Enhancing Long-term Rollout of Neural Operators via Spatially-Adaptive Jacobian Regularization [0.0]
  Jacobian-Adaptive Weighting for Stability (JAWS) is a probabilistic regularization strategy designed to mitigate these limitations.<n>By framing operator learning as Maximum A Posteriori (MAP) estimation with spatially heteroscedastic uncertainty, JAWS dynamically modulates the regularization strength based on local physical complexity.<n> Experiments demonstrate that this spatially-adaptive prior serves as an effective spectral pre-conditioner, which reduces the base operator's burden of handling high-frequency instabilities.
  arXiv  Detail & Related papers  (2026-03-04T06:15:09Z)
• Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients [16.39606116102731]
  The vanishing Polyak delivering adaptive neural network has proven to be a promising choice for gradient descent (SGD)<n> Comprehensive experiments on deep networks corroborate tight convex network theory.<n>In this work, we provide rigorous convergence guarantees for non-smooth optimization with no need for strong assumptions.
  arXiv  Detail & Related papers  (2025-12-02T02:24:32Z)
• Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization [13.97375970293678]
  DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability.<n>We propose Linear Preference Optimization (LPO), a novel alignment framework featuring three key innovations.<n>First, we introduce gradient decoupling by replacing the log-sigmoid function with an absolute difference loss, thereby isolating the optimization dynamics.<n>Second, we improve stability through an offset constraint combined with a positive regularization term to preserve the chosen response quality.<n>Third, we implement controllable rejection suppression using gradient separation with straightforward estimation and a tunable coefficient that linearly regulates the descent of the rejection probability.
  arXiv  Detail & Related papers  (2025-08-20T10:17:29Z)
• SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training [25.244065166421517]
  Low-rank gradient-based optimization methods have significantly improved memory efficiency during the training of large language models (LLMs)<n>These methods primarily emphasize memory savings, often overlooking potential acceleration in convergence.<n>In this paper, we propose SUMO (Subspace-Aware Moment-Orthogonalization), an norm that employs exact singular value decomposition.<n>We show that SUMO accelerates convergence, enhances stability, improves performance, and reduces memory requirements by up to 20% compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-30T16:08:40Z)
• Adaptive Deadline and Batch Layered Synchronized Federated Learning [66.93447103966439]
  Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner.<n>We propose ADEL-FL, a novel framework that jointly optimize per-round deadlines and user-specific batch sizes for layer-wise aggregation.
  arXiv  Detail & Related papers  (2025-05-29T19:59:18Z)
• Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation [73.04087903322237]
  We formulate throughput optimisation as Continual Reinforcement Learning of control policies. Simulation results suggest that the proposed system is able to shorten the end-to-end deployment lead-time by two-fold.
  arXiv  Detail & Related papers  (2024-04-30T11:23:31Z)
• Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup [90.26270347459915]
  We propose a novel momentum-based algorithm via utilizing the global descent locally adaptive. textitLADA could greatly reduce the communication rounds and achieves higher accuracy than several baselines.
  arXiv  Detail & Related papers  (2023-07-30T14:53:21Z)
• Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs [113.8752163061151]
  We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs)<n>We propose the underlineperiodically underlinerestarted underlineoptimistic underlinepolicy underlineoptimization algorithm (PROPO)<n>PROPO features two mechanisms: sliding-window-based policy evaluation and periodic-restart-based policy improvement.
  arXiv  Detail & Related papers  (2021-10-18T02:33:20Z)
• Iterative Amortized Policy Optimization [147.63129234446197]
  Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control. From the variational inference perspective, policy networks are a form of textitamortized optimization, optimizing network parameters rather than the policy distributions directly. We demonstrate that iterative amortized policy optimization, yields performance improvements over direct amortization on benchmark continuous control tasks.
  arXiv  Detail & Related papers  (2020-10-20T23:25:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.