94 citations · 391 across the 65 of their papers we have counts for
14 papers · 1 filter
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
Daniel Pfrommer, Max Simchowitz, Tyler Westenbroek +2
A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e.g.~ - on the lea…
The noise level in linear regression with dependent data
Ingvar Ziemann, Stephen Tu, George J. Pappas +1
We derive upper bounds for random design linear regression with dependent (-mixing) data absent any realizability assumptions. In contrast to the strictly realizable martingale…
Multi-Task Imitation Learning for Linear Dynamical Systems
Thomas T. Zhang, Katie Kang, Bruce D. Lee +4
We study representation learning for efficient imitation learning over linear systems. In particular, we consider a setting where learning is split into two phases: (a) a pre-train…
Toward Certified Robustness Against Real-World Distribution Shifts
Haoze Wu, Teruhiro Tagomori, Alexander Robey +6
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications…
Learning to Control Linear Systems can be Hard
Anastasios Tsiamis, Ingvar Ziemann, Manfred Morari +2
In this paper, we study the statistical difficulty of learning to control linear systems. We focus on two standard benchmarks, the sample complexity of stabilization, and the regre…
TaSIL: Taylor Series Imitation Learning
Daniel Pfrommer, Thomas T. C. K. Zhang, Stephen Tu +1
We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control. TaSIL penalizes deviations in t…
Single Trajectory Nonparametric Learning of Nonlinear Dynamics
Ingvar Ziemann, Henrik Sandberg, Nikolai Matni
Given a single trajectory of a dynamical system, we analyze the performance of the nonparametric least squares estimator (LSE). More precisely, we give nonasymptotic expected …
Linear Variational State-Space Filtering
Daniel Pfrommer, Nikolai Matni
We introduce Variational State-Space Filters (VSSF), a new method for unsupervised learning, identification, and filtering of latent Markov state space models from raw pixels. We p…
Adversarially Robust Stability Certificates can be Sample-Efficient
Thomas T. C. K. Zhang, Stephen Tu, Nicholas M. Boffi +2
Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinea…
How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
Jingxi Xu, Bruce Lee, Nikolai Matni +1
The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. W…
On the Sample Complexity of Stability Constrained Imitation Learning
Stephen Tu, Alexander Robey, Tingnan Zhang +1
We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample…
Learning Stability Certificates from Data
Nicholas M. Boffi, Stephen Tu, Nikolai Matni +2
Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guara…
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
Sangdon Park, Osbert Bastani, Nikolai Matni +1
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i…
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
Sarah Dean, Horia Mania, Nikolai Matni +2
We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the…