Stephen Tu

On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry COLT 2026 Shallow diffusion networks provably learn hidden low-dimensional structure ICLR 2025 Learning from many trajectories JMLR 2024 Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss ICML 2024 Agile Catching with Whole-Body MPC and Blackbox Policy Learning L4DC 2023 Bootstrapped Representations in Reinforcement Learning ICML 2023 Multi-Task Imitation Learning for Linear Dynamical Systems L4DC 2023 Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners CoRL 2023 The noise level in linear regression with dependent data NeurIPS 2023 The Power of Learned Locally Linear Models for Nonlinear Policy Optimization ICML 2023 Adversarially Robust Stability Certificates can be Sample-Efficient L4DC 2022 Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation CoRL 2022 Learning with little mixing NeurIPS 2022 Nonparametric adaptive control and prediction: theory and randomized algorithms JMLR 2022 On the Generalization of Representations in Reinforcement Learning AISTATS 2022 On the Sample Complexity of Stability Constrained Imitation Learning L4DC 2022 TaSIL: Taylor Series Imitation Learning NeurIPS 2022 The role of optimization geometry in single neuron learning AISTATS 2022 Regret Bounds for Adaptive Nonlinear Control L4DC 2021 Safely Learning Dynamical Systems from Short Trajectories L4DC 2021 Learning Hybrid Control Barrier Functions from Data CoRL 2020 Learning Stability Certificates from Data CoRL 2020 Observational Overfitting in Reinforcement Learning ICLR 2020 Certainty Equivalence is Efficient for Linear Quadratic Control NeurIPS 2019 Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator NeurIPS 2019 The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint COLT 2019 Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification COLT 2018 Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator ICML 2018 Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator NeurIPS 2018 Breaking Locality Accelerates Block Gauss-Seidel ICML 2017 Cyclades: Conflict-free Asynchronous Machine Learning NeurIPS 2016 Low-rank Solutions of Linear Matrix Equations via Procrustes Flow ICML 2016 Fast Databases with Fast Durability and Recovery Through Multicore Parallelism OSDI 2014