Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time

We consider the problem of training a multi-layer over-parametrized neural network to minimize the empirical risk induced by a loss function. In the typical setting of over-parametrization, the network width m is much larger than the data dimension d and the number of training samples n (m=poly(n,d)), which induces a prohibitive large weight matrix W∈ ℝm× m per layer. Naively, one has to pay O(m2) time to read the weight matrix and evaluate the neural network function in both forward and backward computation. In this work, we show how to reduce the training cost per iteration. Specifically, we propose a framework that uses m2 cost only in the initialization phase and achieves a truly subquadratic cost per iteration in terms of m, i.e., m2-Omega(1) per iteration. Our result has implications beyond standard over-parametrization theory, as it can be viewed as designing an efficient data structure on top of a pre-trained large model to further speed up the fine-tuning process, a core procedure to deploy large language models (LLM).