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.
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: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.
arXiv:2606. 27315v1 Announce Type: new Abstract: Gradient equilibrium (GEQ) is a recently introduced online optimization framework that generalizes first-order stationarity from offline optimization and abstracts problems like online conformal prediction.
arXiv:2609.06881v1 Announce Type: new Abstract: We study a two-server load balancing system with heterogeneous service rates that are a priori unknown to the dispatcher. The goal is to route customer...
arXiv:2609.07566v1 Announce Type: new Abstract: Caching systems often rely on simple eviction policies such as Least Recently Used (LRU) and Least Frequently Used (LFU), which perform well in complem...
arXiv:2512. 18390v2 Announce Type: replace Abstract: Organizations often have an incumbent predictive model in production when new data sources become available.
arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.
arXiv:2610. 10499v1 Announce Type: new Abstract: Online learning is an attractive framework in many domains because it permits well-defined learning even when data are dependent or chosen adversarially.
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:2510. 21431v2 Announce Type: replace-cross Abstract: We study the combinatorial semi-bandit problem where an agent selects a subset of base arms and receives individual feedback.
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...
arXiv:2610. 11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting.