CORTEXA
← Browse
arxivcs.LG2026-07-22

Online Variance Reduction for Domain Adaptation on Streaming Data

Andrea Napoli

This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, these are incompatible with online, distributed, or incremental learning settings. This paper presents Adaptive vaRiance Reduction via Online reWeighting (ARROW), the first online SVR algorithm for the MMD and CORAL for streamed data. The method maintains moving average references of the alignment statistics, and adaptively reweights incoming minibatches so that the minibatch and reference statistics are aligned. Further, we propose a relaxed reweighting scheme so that the ensuing weight-optimisation problem is tractable. In experiments and simulations, we show that ARROW performs competitively with offline algorithms in terms of runtime, degree of variance reduction achieved, and target domain accuracy.

View free PDFSource page

Related papers

arxivcs.CVcs.LG2026-07-20

DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation

Siobhan Reid, Zhixiang Chi, Li Gu, Omid Reza Heidari, Ziqiang Wang, Yang Wang

Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples. This setting is more realistic than typical domain adaptation setups, which assume access to target data during source training. However, prior…

View free PDFSource page
arxivcs.LGcs.AI2026-07-17

DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning

Hanyang Chen, Anirudh Satheesh, Longchao Da, Hua Wei

Transferring policies across domains poses a vital challenge in reinforcement learning, due to the dynamics mismatch between the source and target domains. In this paper, we consider the setting of online dynamics adaptation, where policies are trained in the source domain with s…

View free PDFSource page
arxivcs.CVcs.LG2026-07-15

XCT-SAM: Sequential Parameter-Efficient Domain Adaptation of SAM for Industrial XCT Defect Segmentation

Md Mahedi Hasan, Md Mushfiqur Rahaman, Alan Pachkovskiy, Imtiaz Ahmed, Jeremy Dawson, Srinjoy Das

Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions. Although recent foundation models such as the Segment Anything Model (SAM) provide str…

View free PDFSource page
arxivcs.LGphysics.ao-ph2026-07-06

Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift

Shuochen Wang, Nishant Yadav, Auroop R. Ganguly

Deep-learning-based climate downscaling aims to learn relationships from historical low-resolution (LR) and high-resolution (HR) climate data to generate HR climate projections. However, this setting faces a temporal out-of-distribution (OOD) challenge: models trained on historic…

View free PDFSource page
arxivcs.LG2026-07-04

NeuroOnline: Bridging Pretraining and Online Adaptation for EEG Foundation Models

Weibin Li, Wendu Li, Yushan You, Chen Wei, Quanying Liu

EEG foundation models have shown strong potential in learning generalized representations across subjects and tasks. However, most existing approaches follow a pretraining-static deployment paradigm, which suffers from two key limitations: (1) misalignment between pretraining obj…

View free PDFSource page