The paper introduces a straightforward framework that transforms dynamic regret minimization into switching regret minimization by constructing an unbiased random sequence for any comparator sequence. Using this reduction, the authors derive dynamic regret bounds for strongly convex and exp-concave losses of “~O(T^{1/3}P_T^{2/3})” and for general convex losses of “O(√{T(1+P_T)})”, matching known minimax optimal results. The approach leverages off-the-shelf switching regret algorithms and controlled variance to achieve these bounds.
By Yibo Wang, Wenhao Yang, Sifan Yang, Yuanyu Wan, Lijun Zhang
arXiv:2602. 06902v3 Announce Type: replace Abstract: In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs.
By Hao Qiu, Andrew Jacobsen, Emmanuel Esposito, Mengxiao Zhang
arXiv:2609. 06921v1 Announce Type: cross Abstract: We study constrained online convex optimization with adversarial constraints when constraint values and gradients are observed through unbiased noise.
By Vaneet Aggarwal
arXiv:2607. 27073v1 Announce Type: new Abstract: We study online convex optimization (OCO) in non-stationary environments under heavy-tailed noise, where the stochastic gradient oracle admits only a finite $p$-th central moment for some $p \in (1, 2]$.
By Vaneet Aggarwal
arXiv:2607. 27073v2 Announce Type: replace-cross Abstract: We study online convex optimization with stochastic gradient noise whose conditional $p$-th central moment is bounded by $\sigma^p$, for an unknown $p\in(1,2]$.
By Vaneet Aggarwal
arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.
By Jiamin Xu, Kyra Gan
The paper introduces Online Hyperparameter Optimization (OHPO), framing it as an infinitely many‑armed bandit problem over mixed and conditional search spaces. It proposes the IMABO framework, which couples any bandit policy with any oracle for proposing new configurations, and presents IMOSS—a restart‑free anytime policy with provable regret bounds. Experiments show that IMABO, combined with practical oracles such as TPE, an incumbent‑mutation oracle, and a pretrained tabular foundation model, outperforms random search across a range of settings from classical ML models to LLM‑based agents.
By Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
arXiv:2605. 21107v2 Announce Type: replace Abstract: We study constrained online convex optimization with adversarial time-varying constraints.
By Dhruv Sarkar, Abhishek Sinha
arXiv:2606. 03831v1 Announce Type: new Abstract: This paper investigates non-stationary online learning using the metric of interval regret, which requires an online algorithm to perform well over every time interval.
By Yan-Feng Xie, Shuche Wang, Peng Zhao, Zhi-Hua Zhou
The paper introduces Drift‑Aware Sparse Routing (DRS), a method for routing requests in a multi‑model language service while respecting compute, latency, memory, or cost budgets. DRS estimates reward and resource use from a rolling audit window, routes using pessimistic reward and optimistic cost estimates, updates resource shadow prices online, and applies a hard meter before commitment. The authors provide theoretical regret bounds that separate control from statistics, showing how the method adapts to non‑stationary prompt distributions and model changes.
By Cheung Hao Lee, Patrick Wong
arXiv:2607. 20769v1 Announce Type: new Abstract: Learning-enabled decision systems often use offline data or computation to reduce online compute cost.
By Shijie Pan, Agustin Castellano, Zeyu Shen, Enrique Mallada
arXiv:2606. 11711v1 Announce Type: new Abstract: Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives.
By Alexander Ryabchenko, Idan Attias, Daniel M. Roy