Scholar
Jian Qian
Google Scholar ID: RTFd7KwAAAAJ
MIT
Citations & Impact
Citations
592
H-index
10
i10-index
10
Publications
18
Co-authors
6
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several preprints and conference papers, including works presented at NeurIPS, ICML, and AISTATS. Specific publications include:
- - To bootstrap or to rollout? An optimal and adaptive interpolation
- - Refined Risk Bounds for Unbounded Losses via Transductive Priors
- - The Statistical Complexity of Interactive Decision Making
- - Bridging multiple worlds: multi-marginal optimal transport for causal partial-identification problem
- - Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
- - Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
- - Online Estimation via Offline Estimation: An Information-Theoretic Framework
- - How Does Variance Shape the Regret in Contextual Bandits?
- - The Non-linear F-Design and Applications to Interactive Learning
- - Model-free reinforcement learning with the decision-estimation coefficient
- - Convex and Non-Convex Optimization under Generalized Smoothness
- - Byzantine-robust federated linear bandits
- - Robust Learning Under Clean-label Attack
- - Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
- - Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes
- - Importance Resampling for Off-policy Prediction
- - Concentration inequalities for multinoulli random variables
Research Experience
- Teaching Assistant for Dynamic Programming & Reinforcement Learning (Spring 2022).
Education
- Pursuing a Ph.D. at MIT EECS, advised by Sasha Rakhlin.
Background
- A final-year Ph.D. student at MIT EECS, focusing on the intersection between machine learning theory and interactive decision making, including online learning, bandits, and reinforcement learning.
Miscellany
- Email: jianqian@mit.edu; [Google Scholar]
