Skip to yearly menu bar Skip to main content

Workshop: Over-parameterization: Pitfalls and Opportunities

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?

Niladri Chatterji · Phil Long · Peter Bartlett


We establish conditions under which gradient descent applied to fixed-width deep networks drives the logistic loss to zero, and prove bounds on the rate of convergence. Our analysis applies for smoothed approximations to the ReLU, such as Swish and the Huberized ReLU, proposed in previous applied work. We provide two sufficient conditions for convergence. The first is simply a bound on the loss at initialization. The second is a data separation condition used in prior analyses.