Can I read Gradient Descent Learns Linear Dynamical Systems on EtoBox?

Gradient Descent Learns Linear Dynamical Systems by Hardt, Moritz; Ma, Tengyu; Recht, Benjamin is a scholarly article available to read on EtoBox.

What is Gradient Descent Learns Linear Dynamical Systems about?

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running time and sample complexity bounds under strong but natural assumptions. Linear systems identification has been studied for many decades, yet, to the best of our knowledge, these are the first polynomial guarantees for the problem we consider.

Author

Hardt, Moritz; Ma, Tengyu; Recht, Benjamin

Published

2016

Language

EN