This is the authors' abstract. We don't add key points for this paper.
We introduce algorithms for learning nonlinear dynamical systems of the form xₜ₊₁=σ(Θ^xₜ)+εₜ, where Θ^ is a weight matrix, $σ$ is a nonlinear link function, and εₜ is a mean-zero noise process. We give an algorithm that recovers the weight matrix Θ^ 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^ (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.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Foster et al. (2020) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: