conftrace_
← Authors

Xuezhou Zhang

26 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+12 more ↓ 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (3)
🐝 Cross-Pollinator (3) 🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (41) 🀝 Dynamic Duo (11) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ’Ž Century Club (26) πŸš€ Conference Pioneer ⚑ Prolific Year (8) πŸ—ƒοΈ Keyword Collector (124) πŸ”₯ Unstoppable (8)

Conferences

NIPS (8) ICML (6) AISTATS (4) AAAI (3) COLT (2) ICLR (2) L4DC (1)

Top co-authors

Xiaojin Zhu (11) Mengdi Wang (9) Wen Sun (6) Yuzhe Ma (5) Chengzhuo Ni (4) Adish Singla (4) Yiding Chen (4) Yuda Song (3) Alekh Agarwal (2) Masatoshi Uehara (2)

Research topics

Privacy (1)

Keywords

reinforcement learning (8) regret bound (5) representation learning (4) sample complexity (3) adversarial learning (3) offline reinforcement learning (2) policy optimization (2) maximum likelihood estimation (2) online learning (2) pessimistic value iteration (2) robust mean estimation (2) adversarial attack (2) value iteration (2) policy gradient (2) asymptotic normality (2) convex optimization (1) data poisoning (1) adversarial robustness (1) feature attribution (1) statistical inference (1)

Papers

Efficient Reinforcement Learning in Probabilistic Reward Machines AAAI 2025 Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption AAAI 2024 State-free Reinforcement Learning NIPS 2024 Scale-free Adversarial Reinforcement Learning COLT 2024 Representation Learning for Low-rank General-sum Markov Games ICLR 2023 Byzantine-Robust Online and Offline Distributed Reinforcement Learning AISTATS 2023 Provable Benefits of Representational Transfer in Reinforcement Learning COLT 2023 Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP ICML 2023 Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback NIPS 2023 Optimal Estimation of Policy Gradient via Double Fitted Iteration ICML 2022 Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach ICML 2022 Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks NIPS 2022 Provable Defense against Backdoor Policies in Reinforcement Learning NIPS 2022 Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization NIPS 2022 Representation Learning for Online and Offline RL in Low-rank MDPs ICLR 2022 Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory ICML 2022 Corruption-robust Offline Reinforcement Learning AISTATS 2022 Neural Additive Models: Interpretable Machine Learning with Neural Nets NIPS 2021 The Sample Complexity of Teaching by Reinforcement on Q-Learning AAAI 2021 Robust Policy Gradient against Strong Data Corruption ICML 2021 Online Data Poisoning Attacks L4DC 2020 Task-agnostic Exploration in Reinforcement Learning NIPS 2020 Adaptive Reward-Poisoning Attacks against Reinforcement Learning ICML 2020 An Optimal Control Approach to Sequential Machine Teaching AISTATS 2019 Policy Poisoning in Batch Reinforcement Learning and Control NIPS 2019 Teacher Improves Learning by Selecting a Training Subset AISTATS 2018