Training Large Neural Networks With Low-Dimensional Error Feedback

TL;DR

This paper introduces a low-dimensional error feedback method for training large neural networks, matching traditional backpropagation performance while being more biologically plausible and computationally efficient.

Contribution

It presents a novel local learning rule based on Feedback Alignment that uses low-dimensional error signals, extending to complex architectures and challenging the need for high-dimensional gradients.

Findings

Low-dimensional error signals can match backpropagation performance.

The method enables efficient training of convolutional and transformer networks.

It offers a biologically plausible alternative to traditional gradient-based learning.

Abstract

Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. However, since most tasks involve low-dimensional outputs, we propose that low-dimensional error signals may suffice for effective learning. To test this hypothesis, we introduce a novel local learning rule based on Feedback Alignment that leverages indirect, low-dimensional error feedback to train large networks. Our method decouples the backward pass from the forward pass, enabling precise control over error signal dimensionality while maintaining high-dimensional representations. We begin with a detailed theoretical derivation for linear networks, which forms the foundation of our learning framework, and extend our approach to nonlinear, convolutional, and transformer architectures. Remarkably, we demonstrate that even minimal error dimensionality on the order of the task dimensionality can achieve performance matching that of traditional backpropagation. Furthermore, our rule enables efficient training of convolutional networks, which have previously been resistant to Feedback Alignment methods, with minimal error. This breakthrough not only paves the way toward more biologically accurate models of learning but also challenges the conventional reliance on high-dimensional gradient signals in neural network training. Our findings suggest that low-dimensional error signals can be as effective as high-dimensional ones, prompting a reevaluation of gradient-based learning in high-dimensional systems. Ultimately, our work offers a fresh perspective on neural network optimization and contributes to understanding learning mechanisms in both artificial and biological systems.