pith. sign in

arxiv: 1609.05191 · v2 · pith:BZCEU7UFnew · submitted 2016-09-16 · 💻 cs.LG · cs.DS· math.OC· stat.ML

Gradient Descent Learns Linear Dynamical Systems

classification 💻 cs.LG cs.DSmath.OCstat.ML
keywords lineardescentdynamicalgradientobjectivepolynomialsystemsystems
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets

    math.OC 2026-05 unverdicted novelty 7.0

    Optimistic bilevel optimization with manifold lower-level minimizers is differentiable if the optimistic selection is unique, yielding a pseudoinverse hyper-gradient and a convergent HG-MS algorithm whose rate depends...

  2. Structure learning of Hamiltonians from real-time evolution

    quant-ph 2024-04 unverdicted novelty 7.0

    New algorithm learns unknown local Hamiltonians from real-time evolution with total time O(log n / ε), without knowing terms, for bounded-norm interactions.

  3. Introduction to Online Control

    cs.LG 2022-11 unverdicted novelty 2.0

    An introduction to online nonstochastic control that applies online convex optimization and convex relaxations to achieve low regret against the best hindsight policy in adversarial settings for classical control problems.