Log In Sign Up

Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems

by   Yahya Sattar, et al.

We consider the problem of learning stabilizable systems governed by nonlinear state equation h_t+1=ϕ(h_t,u_t;θ)+w_t. Here θ is the unknown system dynamics, h_t is the state, u_t is the input and w_t is the additive noise vector. We study gradient based algorithms to learn the system dynamics θ from samples obtained from a single finite trajectory. If the system is run by a stabilizing input policy, we show that temporally-dependent samples can be approximated by i.i.d. samples via a truncation argument by using mixing-time arguments. We then develop new guarantees for the uniform convergence of the gradients of empirical loss. Unlike existing work, our bounds are noise sensitive which allows for learning ground-truth dynamics with high accuracy and small sample complexity. Together, our results facilitate efficient learning of the general nonlinear system under stabilizing policy. We specialize our guarantees to entry-wise nonlinear activations and verify our theory in various numerical experiments


page 1

page 2

page 3

page 4


Stochastic Gradient Descent Learns State Equations with Nonlinear Activations

We study discrete time dynamical systems governed by the state equation ...

Learning nonlinear dynamical systems from a single trajectory

We introduce algorithms for learning nonlinear dynamical systems of the ...

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

We consider the setting of vector valued non-linear dynamical systems X_...

Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms

Two timescale stochastic approximation (SA) has been widely used in valu...

Online Stochastic Gradient Descent Learns Linear Dynamical Systems from A Single Trajectory

This work investigates the problem of estimating the weight matrices of ...

Non-asymptotic Identification of LTI Systems from a Single Trajectory

We consider the problem of learning a realization for a linear time-inva...

LEADS: Learning Dynamical Systems that Generalize Across Environments

When modeling dynamical systems from real-world data samples, the distri...