SGD and Weight Decay Provably Induce a Low-Rank Bias in Neural Networks

Tomer Galanti, Zachary S Siegel, Aparna Gupte, Tomaso Poggio

Abstract:

We analyze deep ReLU neural networks trained with mini-batch Stochastic Gradient Descent (SGD) and weight decay. We show, both theoretically and empirically, that when training a neural network using SGD with weight decay and small batch size, the resulting weight matrices tend to be of small rank. Our analysis relies on a minimal set of assumptions; the neural networks may be arbitrarily wide or deep and may include residual connections, as well as convolutional layers.
The same analysis implies the inherent presence of SGD ``noise'', defined as the inability of SGD to converge to a stationary point. In particular, we prove that SGD noise must always be present, even asymptotically, as long as we incorporate weight decay and the batch size is smaller than the total number of training samples.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning