3 papers
cs.LG2020
A Practical Layer-Parallel Training Algorithm for Residual Networks
Qi Sun, Hexin Dong, Zewei Chen +5
Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which a…
stat.ML2018
On the Approximation Properties of Random ReLU Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by r…
cs.LG2018
But How Does It Work in Theory? Linear SVM with Random Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
We prove that, under low noise assumptions, the support vector machine with random features (RFSVM) can achieve the learning rate faster than on a training…