← Back to all news
arXiv AI By Salim Khazem, Ibrahim Mohamed Serouis

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

Read the original on arXiv AI →

The paper introduces CASTER, a gradient‑free test‑time adaptation method that keeps the model frozen by storing source class statistics in a discriminative subspace and applying an affine transformation estimated from target‑batch moments. CASTER avoids backward passes, optimizer state, and large feature banks, outperforming k‑NN on frozen features in most backbone‑dataset settings while using far less memory. The authors also propose a residual‑to‑margin transportability certificate that flags when affine transport is unreliable, and demonstrate that gating based on this certificate can recover performance losses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 3

FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers

FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.

By Muhammad Rehan, Haider Ali, Muhammad Ali Munir, Moaz Amjad
efficiency
More like this →
arXiv AI
Oct 1

dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale

The paper introduces dattri-LLM, a library designed to make training data attribution (TDA) practical for large language models. It achieves efficiency by using compact gradient representations and a cost‑based routing system, while maintaining compatibility by capturing per‑example gradients from existing training loops without modifications, even in distributed settings. The library also offers extensibility through reusable gradient operations and callbacks, supporting various attribution methods and applications such as online data selection, and demonstrates significant performance gains and scalability up to 110B‑parameter models.

By Shixuan Liu, Tongli Zhou, Junwei Deng, Pingbang Hu, Jiaqi W. Ma
llmsefficiency
More like this →