Stephen Tu

Roy Frostig

Mahdi Soltanolkotabi

J. Mach. Learn. Res., 2024

Shallow diffusion networks provably learn hidden low-dimensional structure.

[BibT_eX]

[DOI]

CoRR, 2024

Incremental Composition of Learned Control Barrier Functions in Unknown Environments.

[BibT_eX]

[DOI]

CoRR, 2024

Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Revisiting Energy Based Models as Policies: Ranking Noise Contrastive Estimation and Interpolating Energy Models.

[BibT_eX]

[DOI]

Sumeet Singh

Krzysztof Marcin Choromanski

Vikas Sindhwani

CoRR, 2023

Safely Learning Dynamical Systems.

[BibT_eX]

[DOI]

CoRR, 2023

The noise level in linear regression with dependent data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Multi-Task Imitation Learning for Linear Dynamical Systems.

[BibT_eX]

[DOI]

Thomas T. C. K. Zhang

Proceedings of the Learning for Dynamics and Control Conference, 2023

Agile Catching with Whole-Body MPC and Blackbox Policy Learning.

[BibT_eX]

[DOI]

Saminda Abeyruwan

Alex Bewley

Nicholas Matthew Boffi

Proceedings of the Learning for Dynamics and Control Conference, 2023

Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Bootstrapped Representations in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2023

2022

Nonparametric adaptive control and prediction: theory and randomized algorithms.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2022

Learning with little mixing.

[BibT_eX]

[DOI]

Ingvar M. Ziemann

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

TaSIL: Taylor Series Imitation Learning.

[BibT_eX]

[DOI]

Daniel Pfrommer

Thomas T. C. K. Zhang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Adversarially Robust Stability Certificates can be Sample-Efficient.

[BibT_eX]

[DOI]

Thomas T. C. K. Zhang

Krzysztof Marcin Choromanski

Proceedings of the Learning for Dynamics and Control Conference, 2022

On the Sample Complexity of Stability Constrained Imitation Learning.

[BibT_eX]

[DOI]

Proceedings of the Learning for Dynamics and Control Conference, 2022

Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation.

[BibT_eX]

[DOI]

Xuesu Xiao

Tingnan Zhang

Proceedings of the Conference on Robot Learning, 2022

On the Generalization of Representations in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

The role of optimization geometry in single neuron learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations.

[BibT_eX]

[DOI]

CoRR, 2021

Random features for adaptive nonlinear control and prediction.

[BibT_eX]

[DOI]

CoRR, 2021

Closing the Closed-Loop Distribution Shift in Safe Imitation Learning.

[BibT_eX]

[DOI]

Alexander Robey

CoRR, 2021

Regret Bounds for Adaptive Nonlinear Control.

[BibT_eX]

[DOI]

Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, 2021

Safely Learning Dynamical Systems from Short Trajectories.

[BibT_eX]

[DOI]

Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, 2021

Learning Robust Hybrid Control Barrier Functions for Uncertain Systems.

[BibT_eX]

[DOI]

Proceedings of the 7th IFAC Conference on Analysis and Design of Hybrid Systems, 2021

2020

Robust Control of the Sit-to-Stand Movement for a Powered Lower Limb Orthosis.

[BibT_eX]

[DOI]

Octavio Narvaez-Aroche

IEEE Trans. Control. Syst. Technol., 2020

On the Sample Complexity of the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Found. Comput. Math., 2020

Observational Overfitting in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Learning Hybrid Control Barrier Functions from Data.

[BibT_eX]

[DOI]

Proceedings of the 4th Conference on Robot Learning, 2020

Learning Stability Certificates from Data.

[BibT_eX]

[DOI]

Vikas Sindhwani

Proceedings of the 4th Conference on Robot Learning, 2020

Learning Control Barrier Functions from Expert Demonstrations.

[BibT_eX]

[DOI]

Proceedings of the 59th IEEE Conference on Decision and Control, 2020

2019

Sample Complexity Bounds for the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

PhD thesis, 2019

Certainty Equivalent Control of LQR is Efficient.

[BibT_eX]

[DOI]

Horia Mania

CoRR, 2019

Certainty Equivalence is Efficient for Linear Quadratic Control.

[BibT_eX]

[DOI]

Horia Mania

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Karl Krauth

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

A Tutorial on Concentration Bounds for System Identification.

[BibT_eX]

[DOI]

Proceedings of the 58th IEEE Conference on Decision and Control, 2019

From self-tuning regulators to reinforcement learning and back again.

[BibT_eX]

[DOI]

Proceedings of the 58th IEEE Conference on Decision and Control, 2019

Minimax Lower Bounds for H∞-Norm Estimation.

[BibT_eX]

[DOI]

Proceedings of the 2019 American Control Conference, 2019

Safely Learning to Control the Constrained Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Proceedings of the 2019 American Control Conference, 2019

2018

Minimax Lower Bounds for ℋ<sub>∞</sub>-Norm Estimation.

[BibT_eX]

[DOI]

CoRR, 2018

Learning Contracting Vector Fields For Stable Imitation Learning.

[BibT_eX]

[DOI]

Vikas Sindhwani

Mohi Khansari

CoRR, 2018

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification.

[BibT_eX]

[DOI]

Proceedings of the Conference On Learning Theory, 2018

On the Approximation of Toeplitz Operators for Nonparametric H<sub>∞</sub>-norm Estimation.

[BibT_eX]

[DOI]

Proceedings of the 2018 Annual American Control Conference, 2018

2017

On the Approximation of Toeplitz Operators for Nonparametric $\mathcal{H}_\infty$-norm Estimation.

[BibT_eX]

[DOI]

CoRR, 2017

Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification.

[BibT_eX]

[DOI]

CoRR, 2017

Breaking Locality Accelerates Block Gauss-Seidel.

[BibT_eX]

[DOI]

Shivaram Venkataraman

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

Large Scale Kernel Learning using Block Coordinate Descent.

[BibT_eX]

[DOI]

Rebecca Roelofs

Shivaram Venkataraman

CoRR, 2016

CYCLADES: Conflict-free Asynchronous Machine Learning.

[BibT_eX]

[DOI]

Xinghao Pan

Maximilian Lam