2 papers
math.OC2023
Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
Frederik Kunstner, Victor S. Portella, Mark Schmidt +1
The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically opti…
cs.LG2017
Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks
Peter L. Bartlett, Nick Harvey, Chris Liaw +1
We prove new upper and lower bounds on the VC-dimension of deep neural networks with the ReLU activation function. These bounds are tight for almost the entire range of parameters.…