← Search

Sohil Shah

2 accepted papers

2018

Stabilizing Adversarial Nets with Prediction Methods

ICLR 2018poster

Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train. These difficulties come from the fact that optimal weights for adversarial nets correspond to saddle points, and not minimizers, of the loss function. The alternating stochastic gradien…

2016

Estimating Sparse Signals With Smooth Support via Convex Programming and Block Sparsity

CVPR 2016poster

Conventional algorithms for sparse signal recovery and sparse representation rely on l1-norm regularized variational methods. However, when applied to the reconstruction of sparse images, i.e., images where only a few pixels are non-zero, simple l1-norm-based methods ignore poten- tial correlations…

Cited by 7PDFScholar