Abstract:This paper presents the Constrained Multi-Task Representation Learning (CMTRL) framework for linear bandits. We consider T linear bandit tasks in a d dimensional space, which share a common low-dimensional representation of dimension r, where r is much smaller than the minimum of d and T. Furthermore, tasks are constrained so that only actions meeting specific safety or performance requirements are allowed, referred to as conservative (safe) bandits. We introduce a novel algorithm, Safe-Alternating projected Gradient Descent and minimization (Safe-AltGDmin), to recover a low-rank feature matrix while satisfying the given constraints. Building on this algorithm, we propose a multi-task representation learning framework for conservative linear bandits and establish theoretical guarantees for its regret and sample complexity bounds. We presented experiments and compared the performance of our algorithm with benchmark algorithms.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.12176 [cs.LG] |
| (or arXiv:2605.12176v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12176 arXiv-issued DOI via DataCite (pending registration) |
From: Jiabin Lin [view email]
[v1]
Tue, 12 May 2026 14:22:03 UTC (926 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。