Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights

no code implementations • 21 Oct 2023 • Carmel Fiscko, Aayushya Agarwal, Yihan Ruan, Soummya Kar, Larry Pileggi, Bruno Sinopoli

We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN.

Numerical Integration