Scholar
Dongruo Zhou
Google Scholar ID: 1780wr0AAAAJ
Indiana University Bloomington
Citations & Impact
Citations
3,570
H-index
26
i10-index
34
Publications
20
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- Federated In-Context Learning: Iterative Refinement for Improved Answer Quality, ICML 2025
- Provable Zero-Shot Generalization in Offline Reinforcement Learning, ICML 2025
- Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation, UAI 2025
- Safe Decision Transformer with Learning-based Constraints, L4DC 2025
- Breaking the log(1/Δ₂) Barrier: Better Batched Best Arm Identification with Adaptive Grids, ICLR 2025
- Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds, ICLR 2025
- Variance-Dependent Regret Bounds for Non-stationary Linear Bandits, AISTATS 2025
- Uncertainty-Aware Reward-Free Exploration with General Function Approximation, ICML 2024
- Risk Bounds of Accelerated SGD for Overparameterized Linear Regression, ICLR 2024
Background
- Assistant Professor, Department of Computer Science, Indiana University Bloomington
- Research interests focus on the foundations of machine learning, particularly sequential decision-making problems such as bandits and reinforcement learning (RL)
- Interested in nearly optimal statistical complexity for RL with function approximation and provable contextual bandits with neural networks
- Studies theoretical foundations of optimization algorithms for deep learning, including sample complexity of SGD-based methods and stochastic algorithms that escape saddle points
- Recently exploring decision-making algorithms for complex structures (e.g., RL for large language models, hierarchical RL) from both algorithmic and systemic perspectives
