activity
20172020
most citedTheoretical properties of the global optimizer of two layer neural network

26 citations · 30 across the 3 of their papers we have counts for

collaborators

6 papers

math.OC2020

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization

Digvijay Boob, Qi Deng, Guanghui Lan +1

Nonconvex sparse models have received significant attention in high-dimensional machine learning. In this paper, we study a new model consisting of a general convex or nonconvex ob…

cs.LG2019

Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning

Uthaipon Tantipongpipat, Chris Waites, Digvijay Boob +2

We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversari…

cs.DS20192 cited

Flowless: Extracting Densest Subgraphs Without Flow Computations

Digvijay Boob, Yu Gao, Richard Peng +4

We propose a simple and computationally efficient method for dense subgraph discovery, which is a classic problem both in theory and in practice. It is well known that dense subgra…

math.OC20192 cited

Faster width-dependent algorithm for mixed packing and covering LPs

Digvijay Boob, Saurabh Sawlani, Di Wang

In this paper, we give a faster width-dependent algorithm for mixed packing-covering LPs. Mixed packing-covering LPs are fundamental to combinatorial optimization in computer scien…

cs.CC2018

Complexity of Training ReLU Neural Network

Digvijay Boob, Santanu S. Dey, Guanghui Lan

In this paper, we explore some basic questions on the complexity of training neural networks with ReLU activation function. We show that it is NP-hard to train a two-hidden layer f…

cs.LG201726 cited

Theoretical properties of the global optimizer of two layer neural network

Digvijay Boob, Guanghui Lan

In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number o…