About
I am a Research Fellow at the National University of Singapore, advised by Jonathan Scarlett. I received my PhD from Università degli Studi di Milano, supervised by Nicolò Cesa-Bianchi and Wouter Koolen at the Centrum Wiskunde & Informatica (CWI). During my PhD, I also worked closely with Mengxiao Zhang at the University of Iowa.
I am broadly interested in the theoretical foundations of machine learning and the development of algorithms with provable guarantees. Currently, I focus on adaptive and efficient sequential decision-making in multi-agent systems.
I am also interested in applying these methods to AI agent routing in multi-agent and LLM-based systems, enabling adaptive and efficient selection of specialized agents, models, or tools for complex tasks.
Selected Publications
View All →Universal Online Convex Optimization with Delayed Feedback
Hao Qiu†, Andrew Jacobsen†, Emmanuel Esposito, Mengxiao Zhang
Preprint
Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach
Hao Qiu†, Mengxiao Zhang†, Nicolò Cesa-Bianchi
Conference on Learning Theory (COLT 2026)
Exploiting Curvature in Online Convex Optimization with Delayed Feedback
Hao Qiu†, Emmanuel Esposito†, Mengxiao Zhang†
International Conference on Machine Learning (ICML 2025)
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
Hao Qiu†, Andrew Jacobsen†, Emmanuel Esposito†, Mengxiao Zhang†
International Conference on Machine Learning (ICML 2026)
† denotes equal contribution or alphabetical order.