1.1k citations · 3.5k across the 39 of their papers we have counts for
4 papers · 1 filter
QuadConv: Quadrature-Based Convolutions with Applications to Non-Uniform PDE Data Compression
Kevin Doherty, Cooper Simpson, Stephen Becker +1
We present a new convolution layer for deep learning architectures which we call QuadConv -- an approximation to continuous convolution via quadrature. Our operator is developed ex…
One-Pass Sparsified Gaussian Mixtures
Eric Kightley, Stephen Becker
We present a one-pass sparsified Gaussian mixture model (SGMM). Given data points in dimensions, , the model fits Gaussian distributions to and (softly) classifi…
Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions
Zhishen Huang, Stephen Becker
We consider the problem of finding local minimizers in non-convex and non-smooth optimization. Under the assumption of strict saddle points, positive results have been derived for…
Sparse projections onto the simplex
Anastasios Kyrillidis, Stephen Becker, Volkan Cevher and +1
Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the -norm. However, several important le…