From the 1 of 5 linked papers with an AI index.
5 papers
Online Control via Counterfactual Tracking
Yunzong Xu
The paper proposes a counterfactual tracking method for online control of linear dynamical systems that can compete with broad classes of causal policies and provides PAC‑Bayes reg…
Finite-Time Queue Peak Laws in Stochastic Networks: Logarithmic Scaling After Geometric Thresholds
Hao Liang, Cheng Tang, Yunzong Xu
We study finite-horizon queue peaks in generalized switches, a standard stochastic-network model in which many queues share constrained service resources. Arrivals may be dependent…
Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
Anthony Pineci, Yunzong Xu
Online inventory optimization (OIO) is online convex optimization with physical memory: inventory carryover makes the feasible action set depend on the past. A natural principle, u…
Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure
Aleksandrs Slivkins, Yunzong Xu, Shiliang Zuo
We study the greedy (exploitation-only) algorithm in bandit problems with a known reward structure. We allow arbitrary finite reward structures, while prior work focused on a few s…
Blind Network Revenue Management and Bandits with Knapsacks under Limited Switches
David Simchi-Levi, Yunzong Xu, Jinglong Zhao
This paper studies the impact of limited switches on resource-constrained dynamic pricing with demand learning. We focus on the classical price-based blind network revenue manageme…