Spotlight
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
Yuanzhi Li · Yingyu Liang

Tue Dec 4th 10:20 -- 10:25 AM @ Room 220 CD

Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In the overparameterized setting, when the data comes from mixtures of well-separated distributions, we prove that SGD learns a network with a small generalization error, albeit the network has enough capacity to fit arbitrary labels. Furthermore, the analysis provides interesting insights into several aspects of learning neural networks and can be verified based on empirical studies on synthetic data and on the MNIST dataset.

Author Information

Yuanzhi Li (Princeton)
Yingyu Liang (University of Wisconsin Madison)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors