Picture for Ruiquan Huang

Ruiquan Huang

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes

Add code
Nov 12, 2024
Viaarxiv icon

Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups

Add code
Sep 27, 2024
Viaarxiv icon

Non-asymptotic Convergence of Training Transformers for Next-token Prediction

Add code
Sep 25, 2024
Figure 1 for Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Viaarxiv icon

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

Add code
Oct 20, 2023
Viaarxiv icon

Temporal-Distributed Backdoor Attack Against Video Based Action Recognition

Add code
Sep 01, 2023
Viaarxiv icon

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

Add code
Jul 01, 2023
Viaarxiv icon

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

Add code
Jun 14, 2023
Viaarxiv icon

Federated Linear Contextual Bandits with User-level Differential Privacy

Add code
Jun 09, 2023
Figure 1 for Federated Linear Contextual Bandits with User-level Differential Privacy
Figure 2 for Federated Linear Contextual Bandits with User-level Differential Privacy
Viaarxiv icon

Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints

Add code
Jun 09, 2023
Viaarxiv icon

Non-stationary Reinforcement Learning under General Function Approximation

Add code
Jun 01, 2023
Viaarxiv icon