mlsanityData to 14 Oct 2026

Online Variance Reduction for Domain Adaptation on Streaming Data

arXiv 2607.20374 ↗First posted 22 Jul 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

25 of 42 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  4. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  7. 2020In Search of Lost Domain Generalizationcited by 1,054
  8. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  9. 2018Characterizing and Avoiding Negative Transfercited by 229
  10. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  11. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  12. 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
13 more
  1. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  2. 2023Spawrious: A Benchmark for Fine Control of Spurious Correlation Biasescited by 41
  3. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  4. 2014Accelerating Minibatch Stochastic Gradient Descent using Stratified Samplingcited by 21
  5. 2018Active Mini-Batch Sampling using Repulsive Point Processescited by 20
  6. 2023DOS: Diverse Outlier Sampling for Out-of-Distribution Detectioncited by 16
  7. 2021Variance Reduced Training with Stratified Sampling for Forecasting Modelscited by 14
  8. 2021Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGDcited by 12
  9. 2018Accelerating Stochastic Gradient Descent Using Antithetic Samplingcited by 4
  10. 2025Variance Matters: Improving Domain Adaptation via Stratified Samplingcited by 3
  11. 2026A Fast and Effective Method for Euclidean Anticlustering: The Assignment-Based-Anticlustering Algorithmcited by 3
  12. 2025Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudescited by 2
  13. 2026Order Matters: Improving Domain Adaptation by Reordering Datacited by 2

Built on by

Not cited yet.