Training DNNs in O(1) memory with MEM-DFA using Random Matrices

This work presents a method for reducing memory consumption to a constant complexity when training deep neural networks. The algorithm is based on the more biologically plausible alternatives of the backpropagation (BP): direct feedback alignment (DFA) and feedback alignment (FA), which use random matrices to propagate error. The proposed method, memory-efficient direct feedback alignment (MEM-DFA), uses higher independence of layers in DFA and allows avoiding storing at once all activation vectors, unlike standard BP, FA, and DFA. Thus, our algorithms memory usage is constant regardless of the number of layers in a neural network. The method increases the computational cost only by a constant factor of one extra forward pass. The MEM-DFA, BP, FA, and DFA were evaluated along with their memory profiles on MNIST and CIFAR-10 datasets on various neural network models. Our experiments agree with our theoretical results and show a significant decrease in the memory cost of MEM-DFA compared to the other algorithms.