Related papers: Online Learning-to-Defer with Varying Experts

Online Learning-to-Defer with Varying Experts

URL: http://arxiv.org/abs/2605.12340v2
Date: Wed, 20 May 2026 08:16:30 GMT
Title: Online Learning-to-Defer with Varying Experts
Abstract summary: We introduce the first online L2D algorithm for multiclass classification with bandit feedback and a dynamically varying pool of experts.<n>Our method achieves regret guarantees of $O((n+n_e)T2/3)$ in general and $O((n+n_e)sqrtT)$ under a low-noise condition.<n>Experiments on synthetic and real-world datasets demonstrate that our approach effectively extends standard Learning-to-Defer to settings with varying expert availability and reliability.
Score: 6.097236291317658
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batch settings, real-world deployments require handling streaming data, changing expert availability, and shifting expert distribution. We introduce the first online L2D algorithm for multiclass classification with bandit feedback and a dynamically varying pool of experts. Our method achieves regret guarantees of $O((n+n_e)T^{2/3})$ in general and $O((n+n_e)\sqrt{T})$ under a low-noise condition, where $T$ is the time horizon, $n$ is the number of labels, and $n_e$ is the number of distinct experts observed across rounds. The analysis builds on novel $\mathcal{H}$-consistency bounds for the online framework, combined with first-order methods for online convex optimization. Experiments on synthetic and real-world datasets demonstrate that our approach effectively extends standard Learning-to-Defer to settings with varying expert availability and reliability.

Related papers

UCB-type Algorithm for Budget-Constrained Expert Learning [71.67657715154034]
algnameM-LCB is a UCB-style meta-algorithm that provides emphanytime regret guarantees<n>We show how algnameM-LCB extends the classical bandit paradigm to the more realistic scenario of coordinating stateful, self-learning experts under limited resources.
arXiv Detail & Related papers (2025-10-26T12:36:17Z)
Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts [6.792743621449621]
We introduce the first framework for Top-$k$ Learning-to-Defer.<n>It allocates queries to the $k$ most cost-effective entities.<n>We also propose Top-$k(x)$ Learning-to-Defer, an adaptive variant that learns the optimal number of experts per query.
arXiv Detail & Related papers (2025-04-17T14:50:40Z)
Efficient Methods for Non-stationary Online Learning [63.268670895111654]
We present efficient methods for optimizing dynamic regret and adaptive regret.<n>The proposed algorithms require only one gradient query and one function evaluation at each round.<n>We also study an even stronger measure, namely "interval dynamic regret", and reduce the number of projections per round from $O(log2 T)$ to $1$.
arXiv Detail & Related papers (2023-09-16T07:30:12Z)
Anytime Model Selection in Linear Bandits [61.97047189786905]
We develop ALEXP, which has an exponentially improved dependence on $M$ for its regret. Our approach utilizes a novel time-uniform analysis of the Lasso, establishing a new connection between online learning and high-dimensional statistics.
arXiv Detail & Related papers (2023-07-24T15:44:30Z)
Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach [57.92727189589498]
We propose an online convex optimization approach with two different levels of adaptivity. We obtain $mathcalO(log V_T)$, $mathcalO(d log V_T)$ and $hatmathcalO(sqrtV_T)$ regret bounds for strongly convex, exp-concave and convex loss functions.
arXiv Detail & Related papers (2023-07-17T09:55:35Z)
Minimax Optimal Online Imitation Learning via Replay Estimation [47.83919594113314]
We introduce a technique of replay estimation to reduce this empirical variance. We show that our approach achieves the optimal $widetildeO left( min(H3/2 / N, H / sqrtN$)$ dependency.
arXiv Detail & Related papers (2022-05-30T19:29:56Z)
Linear Speedup in Personalized Collaborative Learning [69.45124829480106]
Personalization in federated learning can improve the accuracy of a model for a user by trading off the model's bias. We formalize the personalized collaborative learning problem as optimization of a user's objective. We explore conditions under which we can optimally trade-off their bias for a reduction in variance.
arXiv Detail & Related papers (2021-11-10T22:12:52Z)
$k\ exttt{-experts}$ -- Online Policies and Fundamental Limits [8.84337023214151]
This paper studies the $textttExperts$ problem. The learner selects a subset of $k$ experts from a pool of $N$ experts at each round. The reward obtained by the learner at any round depends on the rewards of the selected experts.
arXiv Detail & Related papers (2021-10-15T06:30:15Z)
Online Apprenticeship Learning [58.45089581278177]
In Apprenticeship Learning (AL), we are given a Markov Decision Process (MDP) without access to the cost function. The goal is to find a policy that matches the expert's performance on some predefined set of cost functions. We show that the OAL problem can be effectively solved by combining two mirror descent based no-regret algorithms.
arXiv Detail & Related papers (2021-02-13T12:57:51Z)
Filtering DDoS Attacks from Unlabeled Network Traffic Data Using Online Deep Learning [7.683035842994701]
DDoS attacks are simple, effective, and still pose a significant threat even after more than two decades. There are challenges in adopting deep learning solutions due to the ever-changing profiles, the lack of labeled data, and constraints in the online setting. In this paper, we propose two frameworks that utilize both the historic $mathcal N$ and the mixture $mathcal M$ traffic obtained during attacks.
arXiv Detail & Related papers (2020-12-12T12:39:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.