The paper studies online algorithms for monotone submodular maximization with full knowledge of the future and unlimited computation. It establishes optimal approximation thresholds of 3/4 for deterministic algorithms and approximately 0.7942 for randomized algorithms, while allowing a constant number of changes per step. The authors provide matching impossibility results and achieve these bounds by balancing preparation for future arrivals with protection of the current solution, using techniques such as interval-selection analysis for randomized algorithms and certificate-based rounding for deterministic ones.
By Eric Balkanski, Paul D\"utting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Ola Svensson, Morteza Zadimoghaddam
arXiv:2610.15461v1 Announce Type: new
Abstract: MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through...
By Tomer Massas, Vadim Indelman
The paper addresses an online resource allocation problem where a budget must be distributed among multiple arms under censored feedback. Each arm yields a reward only if it is activated by an unknown Bernoulli process and the allocated budget exceeds a random threshold from an unknown parametric distribution. The authors establish a worst‑case regret lower bound of Σ(√T), propose the RA‑UCB algorithm achieving near‑optimal regret when the budget is known, and introduce MG‑UCB for unknown, round‑dependent budgets, validating both approaches experimentally.
By Giovanni Montanari, C\^ome Fiegel, Corentin Pla, Aadirupa Saha, Vianney Perchet
arXiv:2610.14996v1 Announce Type: new
Abstract: Choosing a few robust algorithms or schedules can require evaluating every candidate under many adverse scenarios, even though an agent only needs to i...
By Yuhe Sui, Yingzhi Tang
arXiv:2606. 00835v1 Announce Type: new Abstract: Network routers that enforce Quality-of-Service (QoS) guarantees must decide, at every clock cycle, which expiring packet of information to transmit, even when the value of the packet is unknown until it is processed.
By Gianmarco Genalti, Achraf Azize, Vianney Perchet
arXiv:2609.25388v1 Announce Type: cross
Abstract: A classical question in statistics is which observable quantities to condition on when drawing inferences about unobservable targets. For conformal p...
By Xuelin Yang, Baihe Huang, Yilong Hou, Guido Imbens, Michael I. Jordan
This paper studies additive regret in the multi-secretary problem, defined as the gap between the expected offline prophet reward and the reward of the best online policy. Prior work established \(O(\log T)\) regret for bounded-density distributions with connected support and \(O((\log T)^2)\) upper bounds for bounded-density distributions with support gaps.
Consistent submodular maximization studies the tradeoff between solution quality and stability when elements arrive over time. For a monotone submodular objective, which models diminishing returns, an...
arXiv:2607. 02150v1 Announce Type: cross Abstract: This paper studies additive regret in the multi-secretary problem, defined as the gap between the expected offline prophet reward and the reward of the best online policy.
By Jiawei Zhang
arXiv:2509. 20114v3 Announce Type: replace Abstract: We study \emph{online episodic Constrained Markov Decision Processes} (CMDPs) under both stochastic and adversarial constraints.
By Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
arXiv:2610. 02258v1 Announce Type: new Abstract: We study online convex optimization with one unbiased stochastic subgradient per round and an unknown finite conditional $p$th noise moment, $1<p\le2$.
By Vaneet Aggarwal
arXiv:2606.00920v2 Announce Type: replace-cross
Abstract: A benchmark score is a measurement whose uncertainty has two sources: an aleatoric component from stochastic decoding and an epistemic compon...
By Yongxi Zhou, Lai Yun Choi, Jiaxi Wen, Wenbo Ye, Junwei Yao