Online Learning-to-Defer with Varying Experts

[2605.12340] Online Learning-to-Defer with Varying Experts Skip to main content Search Submit Donate Log in Statistics > Machine Learning arXiv:2605.12340 (stat) [Submitted on 12 May 2026 ( v1 ), last revised 28 Aug 2026 (this version, v5)] Title: Online Learning-to-Defer with Varying Experts Authors: Dang Hoang Duy , Yannis Montreuil , Maxime Meyer , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi View PDF HTML (experimental) Abstract: Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. Real-world deployments require handling streaming data, changing expert availability, shifting expert reliability, and feedback observed only for the selected action. We introduce an online multiclass L2D algorithm that combines queried-action bandit feedback with a dynamically varying pool of experts. Let $N=n+n_e$, let $B$ bound the Frobenius norm of the linear score matrix, and let $\rho$ bound the augmented input norm. Assuming linear calibration and zero surrogate minimizability gap for the projected comparator class, our method achieves expected true-deferral regret $O((BN^{3/2}\rho+1)T^{2/3})$, improving to $O(BN^{3/2}\rho\sqrt T+B^2N^3\rho^2)$ under a concentrated-score condition. The analysis combines an online $\mathcal H$-consistency transfer bound with projected online convex optimization. Experiments on synthetic and real-world datasets demonstrate selective routing under varying expert availability and reliability. Subjects: Machine Learning (stat.ML) ; Machine Learning (cs.LG) Cite as: arXiv:2605.12340 [stat.ML] (or arXiv:2605.12340v5 [stat.ML] for this version) https://doi.org/10.48550/arXiv.2605.12340 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yannis Montreuil [ view email ] [v1] Tue, 12 May 2026 16:19:44 UTC (4,227 KB) [v2] Wed, 20 May 2026 08:16:30 UTC (3,191 KB) [v3] Thu, 28 May 2026 09:22:52 UTC (3,192 KB) [v4] Fri, 29 May 2026 07:49:08 UTC (3,192 KB) [v5] Fri, 28 Aug 2026 09:24:45 UTC (4,231 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: stat.ML < prev | next > new | recent | 2026-05 Change to browse by: cs cs.LG stat References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Online Learning-to-Defer with Varying Experts#682674
• Online Learning-to-Defer with Varying Experts#178897
• A Bayesian approach to on-line learning#230087
• DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models#799932
• Prediction-powered Inference by Mixture of Experts#146949