Learning nonlinear dynamical systems from a single trajectory
This addresses the challenge of efficient system identification in machine learning and control, with incremental improvements in assumptions and applicability.
The paper tackles the problem of learning nonlinear dynamical systems from a single trajectory, introducing an algorithm that recovers the weight matrix with optimal sample complexity and linear running time, succeeding under weaker statistical assumptions than prior work.
We introduce algorithms for learning nonlinear dynamical systems of the form $x_{t+1}=σ(Θ^{\star}x_t)+\varepsilon_t$, where $Θ^{\star}$ is a weight matrix, $σ$ is a nonlinear link function, and $\varepsilon_t$ is a mean-zero noise process. We give an algorithm that recovers the weight matrix $Θ^{\star}$ from a single trajectory with optimal sample complexity and linear running time. The algorithm succeeds under weaker statistical assumptions than in previous work, and in particular i) does not require a bound on the spectral norm of the weight matrix $Θ^{\star}$ (rather, it depends on a generalization of the spectral radius) and ii) enjoys guarantees for non-strictly-increasing link functions such as the ReLU. Our analysis has two key components: i) we give a general recipe whereby global stability for nonlinear dynamical systems can be used to certify that the state-vector covariance is well-conditioned, and ii) using these tools, we extend well-known algorithms for efficiently learning generalized linear models to the dependent setting.