In this paper, we present correlated logistic (CorrLog) model for multil...
The stunning empirical successes of neural networks currently lack rigor...
We propose semi-random features for nonlinear function approximation. Th...
Neural networks are a powerful class of functions that can be trained wi...
The general perception is that kernel methods are not scalable, and neur...
Spectral methods have greatly advanced the estimation of latent variable...