Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning
This work addresses interpretability in supervised learning by analyzing training dynamics, but it is incremental as it builds on existing gradient descent theory.
The authors derived explicit gradient flow equations for deep learning with ReLU activations, showing that gradient descent dynamically truncates data clusters at an exponential rate dependent on prior truncations.
We derive explicit equations governing the cumulative biases and weights in Deep Learning with ReLU activation function, based on gradient descent for the Euclidean cost in the input layer, and under the assumption that the weights are, in a precise sense, adapted to the coordinate system distinguished by the activations. We show that gradient descent corresponds to a dynamical process in the input layer, whereby clusters of data are progressively reduced in complexity ("truncated") at an exponential rate that increases with the number of data points that have already been truncated. We provide a detailed discussion of several types of solutions to the gradient flow equations. A main motivation for this work is to shed light on the interpretability question in supervised learning.