Low-rank modeling plays a pivotal role in signal processing and machine learning, with
applications ranging from collaborative filtering, video surveillance, and medical imaging to …

Historically, scalability has been a major challenge for the successful application of
semidefinite programming in fields such as machine learning, control, and robotics. In this …

We study gradient compression methods to alleviate the communication bottleneck in data-
parallel distributed optimization. Despite the significant attention received, current …

We propose a reparametrization scheme to address the challenges of applying differentially
private SGD on large neural networks, which are 1) the huge memory cost of storing …

Convex relaxations have emerged as a promising approach for verifying properties of neural
networks, but widely used using Linear Programming (LP) relaxations only provide …

We consider the recovery of a (real-or complex-valued) signal from magnitude-only
measurements, known as phase retrieval. We formulate phase retrieval as a convex …

Semidefinite programming (SDP) is a powerful framework from convex optimization that has
striking potential for data science applications. This paper develops a provably correct …

This paper describes a suite of algorithms for constructing low-rank approximations of an
input matrix from a random linear image, or sketch, of the matrix. These methods can …

Phase retrieval consists in the recovery of a complex-valued signal from intensity-only
measurements. As it pervades a broad variety of applications, many researchers have …

This paper argues that randomized linear sketching is a natural tool for on-the-fly
compression of data matrices that arise from large-scale scientific simulations and data …