Ph.D. Research Proficiency Exam: Tianxiang Gao

Tianxiang Gao
Tuesday, November 2, 2021 - 2:30pm
1652 Gilman Hall
Event Type: 

A Global Convergence Theory for Deep Relu Implicit Networks Via Over-Parameterization

Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures. Its prediction rule is provided implicitly based on the solution of an equilibrium equation. Although a line of recent empirical studies has demonstrated its superior performances, the theoretical understanding of implicit neural networks is limited. In general, the equilibrium equation may not be well-posed during the training. As a result, there is no guarantee that a vanilla (stochastic) gradient descent (SGD) training nonlinear implicit neural networks can converge. This paper fills the gap by analyzing the gradient flow of Rectified Linear Unit (ReLU) activated implicit neural networks. For an m-width implicit neural network with ReLU activation and n training samples, we show that a randomly initialized gradient descent converges to a global minimum at a linear rate for the square loss function if the implicit neural network is over-parameterized. It is worth noting that, unlike existing works on the convergence of (S)GD on finite-layer over-parameterized neural networks, our convergence results hold for implicit neural networks, where the number of layers is infinite.

Committee: Hongyang Gao (major professor), Jia Liu, Hailiang Liu, Christopher Quinn, and Namrata Vaswani

Join on WebEx:

Meeting number: 2624 273 2647 Password: wPw6MWMUE57