We study the implicit bias towards low-rank weight matrices when training neural networks (NN) with Weight Decay (WD). We prove that when a ReLU NN is sufficiently trained with Stochastic Gradient Descent (SGD) and WD, its weight matrix is approximately a rank-two matrix. Empirically, we demonstrate that WD is a necessary condition for inducing this low-rank bias across both regression and classification tasks. Our work differs from previous studies as our theoretical analysis does not rely on common assumptions regarding the training data distribution, optimality of weight matrices, or specific training procedures. Furthermore, by leveraging the low-rank bias, we derive improved generalization error bounds and provide numerical evidence showing that better generalization can be achieved. Thus, our work offers both theoretical and empirical insights into the strong generalization performance of SGD when combined with WD.
View on arXiv