Xiaoqi Tan

4 papers · 2024–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

AAAI (1) COLT (1) IJCAI (1) NeurIPS (1)

Top co-authors

Csaba Szepesvári (2) John Tyler (1) Ying Cao (1) Alex Ayoub (1) Hasti Nourmohammadi (1) Volodymyr Tkachuk (1) Yunwei Ryan Li (1) Flore Sentenac (1) Shuai Liu (1) Faraz Zargari (1)

Research topics

Machine Learning (3) Mathematics & Optimization (3) Optimization (3) Artificial Intelligence (2) Learning Types (2) Optimization & Theory (2) Reinforcement Learning (1) Core AI (1) Learning Paradigms (1) Mathematics (1) Methods (1) Probability (1)

Keywords

policy evaluation (1) offline reinforcement learning (1) policy optimization (1) function approximation (1) sample complexity (1) exponential family (1) regularized optimization (1) posted-price mechanism (1) online allocation (1) multi-armed bandit (1) regret bound (1) online algorithm (1) secretary problem (1) optimistic algorithm (1) prediction error (1) natural exponential families (1) bandit algorithm (1) generalized linear bandit (1) optimization framework (1) sub-gaussian distribution (1)

Papers

Ordinal Secretaries with Advice AAAI 2026 Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear q^π-Realizability and Concentrability COLT 2026 Cap-and-Penalize: Competitive Mechanisms for Multi-Phase Regularized Online Allocation IJCAI 2025 Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits NeurIPS 2024