activity
20192026
most citedFinite Step Performance of First-order Methods Using Interpolation Conditions Without Function Evaluations

5 citations · 6 across the 5 of their papers we have counts for

collaborators
Showing eess.SYShow all

6 papers · 1 filter

eess.SY2024

Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification

Bruce D. Lee, Anders Rantzer, Nikolai Matni

The strategy of pre-training a large model on a diverse dataset, then fine-tuning for a particular application has yielded impressive results in computer vision, natural language p…

eess.SY2023

Performance-Robustness Tradeoffs in Adversarially Robust Control and Estimation

Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani +1

While methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastica…

eess.SY2023

The Fundamental Limitations of Learning Linear-Quadratic Regulators

Bruce D. Lee, Ingvar Ziemann, Anastasios Tsiamis +2

We present a local minimax lower bound on the excess cost of designing a linear-quadratic controller from offline data. The bound is valid for any offline exploration policy that c…

eess.SY2022

Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control

Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani +1

While methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastica…

eess.SY20205 cited

Finite Step Performance of First-order Methods Using Interpolation Conditions Without Function Evaluations

Bruce Lee, Peter Seiler

We present a procedure to numerically compute finite step worst case performance guarantees on a given algorithm for the unconstrained optimization of strongly convex functions wit…

eess.SY2019

Non-asymptotic Closed-Loop System Identification using Autoregressive Processes and Hankel Model Reduction

Bruce Lee, Andrew Lamperski

One of the primary challenges of system identification is determining how much data is necessary to adequately fit a model. Non-asymptotic characterizations of the performance of s…