Collective evolution of weights in wide neural networks

10/09/2018
by   Dmitry Yarotsky, et al.
0

We derive a nonlinear integro-differential transport equation describing collective evolution of weights under gradient descent in large-width neural-network-like models. We characterize stationary points of the evolution and analyze several scenarios where the transport equation can be solved approximately. We test our general method in the special case of linear free-knot splines, and find good agreement between theory and experiment in observations of global optima, stability of stationary points, and convergence rates.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset