Explaining the Learning Dynamics of Direct Feedback Alignment

Justin Gilmer, Colin Raffel, Samuel S. Schoenholz, Maithra Raghu, and Jascha Sohl-Dickstein

TL;DR: We interpret DFA as a noisy version of a layer-wise training method we call Linear Aligned Feedback Systems (LAFS).

Abstract:

Two recently developed methods, Feedback Alignment (FA) and Direct Feedback Alignment (DFA), have been shown to obtain surprising performance on vision tasks by replacing the traditional backpropagation update with a random feedback update. However, it is still not clear what mechanisms allow learning to happen with these random updates.
In this work we argue that DFA can be viewed as a noisy variant of a layer-wise training method we call Linear Aligned Feedback Systems (LAFS). We support this connection theoretically by comparing the update rules for the two methods. We additionally empirically verify that the random update matrices used in DFA work effectively as readout matrices, and that strong correlations exist between the error vectors used in the DFA and LAFS updates. With this new connection between DFA and LAFS we are able to explain why the "alignment" happens in DFA.

Keywords: Theory, Supervised Learning, Optimization

Conflicts: google.com