arXiv:2510. 19528v2 Announce Type: replace-cross Abstract: We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding.
arXiv:2602. 02061v2 Announce Type: replace Abstract: Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanisms.
The paper introduces Lag, a mean‑field optimal index policy for online assignment problems with reusable resources, such as peer review, call routing, ridesharing, emergency dispatch, and crowdsourcing. By modeling the problem as a contextual restless multi‑armed bandit and deriving an occupancy‑measure linear program, the authors obtain Lag from the dual and prove it is asymptotically optimal in a scaling regime where server copies and arrivals grow together. Experiments on peer‑review and call‑center data show Lag achieves 83–99% of the LP upper bound and outperforms greedy assignment by up to 36% in synthetic settings.
arXiv:2607. 10963v1 Announce Type: cross Abstract: We study the problem of efficient online proportional sampling from a high-dimensional domain under a $\sigma$-smoothed adversary, where the sampling distribution is induced by a dynamically evolving weight function defined over a sequence of piecewise-structured partitions.
arXiv:2607. 23765v1 Announce Type: cross Abstract: Large language models (LLMs) achieve impressive performance across multiple domains, but using the most capable model for every query is prohibitive at scale.
Meta-LinEXP3 is an online-within-online algorithm designed for adversarial linear contextual bandits with random action sets. It builds a task-level prior from completed tasks to guide an inner LinEXP3 learner, achieving an σO(√n) per‑task regret when context distributions are known and an σO(n^{2/3}) regret with a past‑only regularized moment estimator when they are unknown. The paper also links prior accuracy to transfer regret, showing that better priors yield sublinear, transfer‑dependent regret across tasks, and demonstrates the method on structured hyperspectral tensor sampling.
arXiv:2606. 04305v1 Announce Type: new Abstract: We study online learning with an additional offline dataset in the stochastic linear bandit setting.
arXiv:2610.19804v1 Announce Type: new Abstract: We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round...
arXiv:2608.24146v1 Announce Type: new Abstract: In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate...
arXiv:2509. 03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits.
The paper introduces AdaSwitch, a meta‑algorithm for history‑dependent online problems where predictions of future requests may be inaccurate. It operates within a bounded‑influence framework, where past decisions only affect future optimal values by a limited amount, and it adaptively switches between offline and online oracles. AdaSwitch guarantees expected performance that improves as prediction error shrinks or the offline optimum grows, while maintaining a near‑optimal worst‑case bound under arbitrary predictions. The authors demonstrate its applicability to online lead‑time quotation, k‑server and caching, and online reusable resource allocation for both reward maximization and cost minimization.
We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round $t \in [T]$, both player and environment observe...