Profiles2021-2025
Jing Yang
The Pennsylvania State University
17Papers
7Last author
14Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers17
- On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse RecoveryAuthor 4 of 4ICLR 2025
- Efficient Prompt Optimization Through the Lens of Best Arm IdentificationAuthor 5 of 6NeurIPS 2024 · 44 citations
- Federated Q-Learning: Linear Regret Speedup with Low Communication CostAuthor 4 of 4ICLR 2024 · 21 citations
- Federated Representation Learning in the Under-Parameterized RegimeAuthor 3 of 3ICML 2024 · 13 citations
- Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained ModelsAuthor 3 of 4NeurIPS 2024 · 2 citations
- Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upsAuthor 3 of 3NeurIPS 2024 · 1 citation
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov GamesAuthor 4 of 5ICML 2024 · 1 citation
- Provable Benefits of Multi-task RL under Non-Markovian Decision Making ProcessesAuthor 3 of 5ICLR 2024
- Federated Linear Contextual Bandits with User-level Differential PrivacyAuthor 6 of 6ICML 2023 · 17 citations
- Non-stationary Reinforcement Learning under General Function ApproximationAuthor 5 of 6ICML 2023 · 11 citations
- Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise ConstraintsAuthor 4 of 4ICML 2023 · 4 citations
- Provably Efficient Algorithm for Nonstationary Low-Rank MDPsAuthor 2 of 3NeurIPS 2023 · 2 citations
- Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPsAuthor 3 of 4ICLR 2023
- Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RLAuthor 2 of 3ICLR 2023
- Provable Benefit of Multitask Representation Learning in Reinforcement LearningAuthor 3 of 5NeurIPS 2022 · 33 citations
- Federated Linear Contextual BanditsAuthor 3 of 4NeurIPS 2021 · 94 citations
- Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationAuthor 4 of 4NeurIPS 2021 · 33 citations
