Publications (61)
Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
Ingvar Ziemann, Stephen Tu, George J. Pappas +1
In this work, we study statistical learning with dependent (-mixing) data and square loss in a hypothesis class where is the norm $\|f\|_{Î…
Safely Learning Dynamical Systems
Amir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani +1
A fundamental challenge in learning an unknown dynamical system is to reduce model uncertainty by making measurements while maintaining safety. We formulate a mathematical definiti…
Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem
Hesameddin Mohammadi, Mohammad Tinati, Stephen Tu +2
The symmetric low-rank matrix factorization serves as a building block in many learning tasks, including matrix recovery and training of neural networks. However, despite a flurry…
Safely Learning Dynamical Systems from Short Trajectories
Amir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani +1
A fundamental challenge in learning to control an unknown dynamical system is to reduce model uncertainty by making measurements while maintaining safety. In this work, we formulat…
Large Scale Kernel Learning using Block Coordinate Descent
Stephen Tu, Rebecca Roelofs, Shivaram Venkataraman +1
We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points. Armed with this capability, w…
Certainty Equivalence is Efficient for Linear Quadratic Control
Horia Mania, Stephen Tu, Benjamin Recht
We study the performance of the certainty equivalent controller on Linear Quadratic (LQ) control problems with unknown transition dynamics. We show that for both the fully and part…