Jason D Lee

4 papers · 2020–2025 · 1 venue · 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 ↓

🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

COLT (4)

Top co-authors

Yuxin Chen (2) Simon S Du (2) Zihan Zhang (2) Gaurav Mahajan (1) Daniel Hsu (1) Denny Wu (1) Sham M Kakade (1) Alex Damian (1) Zixuan Wang (1) Alberto Bietti (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Artificial Intelligence (2) Reinforcement Learning (2) Methods (2) Natural Language Processing (1) Application Areas (1) Core AI (1) Learning Paradigms (1) Learning Types (1) Resources & Methods (1)

Keywords

sample complexity (3) markov decision process (2) curriculum learning (1) natural policy gradient (1) global convergence (1) transformer (1) computational complexity (1) adaptive sampling (1) empirical risk minimization (1) vc dimension (1) gradient descent (1) online reinforcement learning (1) minimax optimal (1) regret bound (1) convergence rate (1) entropy regularization (1) worst-case risk (1) model-based algorithm (1) multi-distribution learning (1) policy gradient method (1)

Papers

Learning Compositional Functions with Transformers from Easy-to-Hard Data COLT 2025 Optimal Multi-Distribution Learning COLT 2024 Settling the sample complexity of online reinforcement learning COLT 2024 Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes COLT 2020