2 papers
cs.LG2026
Stochastic learning flow: moment equations for stochastic gradient descent at finite step size
Christian Schmid, James M Murray
Analytical theories of learning in deep networks often assume gradient flow, discarding the finite step size and batch noise of stochastic gradient descent (SGD). Starting from the…
cs.LG2024
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Christian Schmid, James M. Murray
The ability of a brain or a neural network to efficiently learn depends crucially on both the task structure and the learning rule. Previous works have analyzed the dynamical equat…