Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You

• URL: http://arxiv.org/abs/2609.00374v1
• Date: Mon, 31 Aug 2026 21:07:36 GMT
• Title: Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You
• Abstract summary: Test-time adaptation assumes that model parameters can be updated at inference time.<n>We study adaptation when the learned model must remain frozen.<n>We introduce CASTER, a method that stores source class statistics in a discriminative subspace.
• Score: 0.8594140167290097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third-party models, and memory-constrained deployments, and standard BatchNorm-based TTA configurations may also become inactive on architectures without BatchNorm. We study adaptation when the learned model must remain frozen. We introduce CASTER, a gradient-free method that stores source class statistics in a discriminative subspace, estimates a class-shared affine transformation from target-batch moments, and analytically transports the source class distributions before classification. CASTER requires no backward pass, optimizer state, or stored source feature bank. Across four backbones and seven datasets, it outperforms k-NN on identical frozen features in 27 of 28 backbone-dataset settings while retaining a median of 18x less state. Affine transport is not always reliable. On ImageNet-C, where batches contain only 64 samples for 1000 classes, unconditional transport loses 21.2 top-1 points. We therefore introduce an empirical residual-to-margin transportability certificate. Across 307 evaluation cells, every transport losing more than 10 points has certificate value above 3.9, although benign and destructive regimes are not perfectly separated. Gating converts an average $-3.35$-point effect of unconditional transport into a +1.69-point gain, and performance remains within 0.3 points of the best threshold over a broad threshold range. Finally, we show that this certificate is mechanism-specific: when applied to Tent, it accepts only $4.3\%$ of updates and preserves 0.6% of Tent's available gain. These results position CASTER as a lightweight adaptation mechanism for frozen-model deployment, together with an explicit account of when its safety signal is informative and when it is not.

Related papers

• Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs [0.0]
  Inference-time steering enables behavioral control of large language models without parameter modification.<n>Post-training quantization reduces memory and compute costs for deployment.<n>We systematically study activation steering under weight-only quantization.
  arXiv  Detail & Related papers  (2026-09-06T08:41:42Z)
• SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation [0.0]
  This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation.<n>We describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation.
  arXiv  Detail & Related papers  (2026-08-31T23:19:59Z)
• SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models [0.0]
  We introduce SpikeWorld, a 1.45M sparse spiking model jointly trained for heterogeneous sensory prediction, semantics, image-text binding and action-conditioned dynamics.<n>Joint optimization improves action next-state MSE by 17.10% while also improving multimodal prediction, semantic accuracy and image-text retrieval.
  arXiv  Detail & Related papers  (2026-08-07T18:57:06Z)
• DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting [0.0]
  DG-FedReuse is a simulator-level mechanism that allows selected clients to contribute cached updates.<n>Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label clients, and three seeds.<n> DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg.
  arXiv  Detail & Related papers  (2026-08-05T19:30:04Z)
• Forgetful Attention: A Trainable Support-Vector Memory with Certified Selection and Exact Unlearning [0.16921396880325776]
  We introduce Support Vector Attention (SV-Attention), a memory whose weights are support coefficients of a one-class Sfp with fixed box parameter C.<n>Its active-set partition gives reserve tokens exactly zero weight, output weights; a incremental incremental solver token to recover the state produced by retraining without it under the same C.<n>We also demonstrate surgical eviction, exact editing, patient-record deletion, and a forgettable retrieval memory over real sentence embeddings.
  arXiv  Detail & Related papers  (2026-07-13T23:13:57Z)
• Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements [23.74905101390208]
  Closed-loop Auto Research extends automated machine learning from fixed-dataset fitting to changing the research workflow.<n>We ask whether this action space yields improvements generalizing beyond the validation signal selecting them.<n>Across 36 endpoints in three benchmark suites we score each selected configuration once on a held-out test whose labels the search never read.
  arXiv  Detail & Related papers  (2026-06-22T00:18:27Z)
• Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers [0.0]
  We present an online monitoring system for distributional shift in deployed safety classifiers.<n>After detection, a conformal abstention layer adapts decision to recover a target error.<n>The system achieves 86.6% detection with mean latency of 39.5800 steps.
  arXiv  Detail & Related papers  (2026-06-10T11:24:25Z)
• Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration [30.310793549183117]
  We introduce Hierarchical Certified Semantic Commitment (H-CSC), a BFT-inspired protocol that converts embedding-derived finality signals over verdict-emitting proposal groups into one of three typed outcomes.<n>H-CSC commits with low angular deviation on BFT-feasible buckets (0.31 to 2.04 degrees) and aborts 100% of beyond-BFT rounds (n3f+1) as intended.
  arXiv  Detail & Related papers  (2026-06-05T14:35:58Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• SNAP: Low-Latency Test-Time Adaptation with Sparse Updates [31.155455736641116]
  Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts.<n>We propose SNAP, a sparse TTA framework that reduces adaptation frequency and data usage while preserving accuracy.<n> SNAP maintains competitive accuracy even when adapting based on only 1% of the incoming data stream.
  arXiv  Detail & Related papers  (2025-11-19T09:40:24Z)
• Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging [33.86980091897939]
  Token Purging (PG) is a backpropagation-free approach that removes tokens highly affected by domain shifts before they reach attention layers.<n>We propose two variants: PG-SP, which leverages source statistics, and PG-SF, a fully source-free version relying on CLS-token-driven adaptation.<n>PG-SP achieves an average of +10.3% higher accuracy than state-of-the-art backpropagation-free methods, while PG-SF sets new benchmarks for source-free adaptation.
  arXiv  Detail & Related papers  (2025-09-11T18:33:40Z)
• Unified Entropy Optimization for Open-Set Test-Time Adaptation [40.111891407629]
  Test-time adaptation (TTA) aims at adapting a model pre-trained on the labeled source domain to the unlabeled target domain. Many state-of-the-art closed-set TTA methods perform poorly when applied to open-set scenarios. We propose a simple but effective framework called unified entropy optimization (UniEnt)
  arXiv  Detail & Related papers  (2024-04-09T07:08:00Z)

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.