Large-scale distributed training of neural networks is often limited by network bandwidth,
wherein the communication time overwhelms the local computation time. Motivated by the …

Estimating the frequencies of elements in a data stream is a fundamental task in data
analysis and machine learning. The problem is typically addressed using streaming …

As computational biologists continue to be inundated by ever increasing amounts of
metagenomic data, the need for data analysis approaches that keep up with the pace of …

Estimating frequencies of elements appearing in a data stream is a key task in large-scale
data analysis. Popular sketching approaches to this problem (eg, CountMin and …

The last decade saw impressive progress towards understanding the performance of
algorithms in adaptive settings, where subsequent inputs may depend on the output from …

We take a random matrix theory approach to random sketching and show an asymptotic first-
order equivalence of the regularized sketched pseudoinverse of a positive semidefinite …

Major complications arise from the recent increase in the amount of high-dimensional data,
including high computational costs and memory requirements. Feature selection, which …

Many popular first-order optimization methods accelerate the convergence rate of deep
learning models. However, these algorithms require auxiliary variables, which cost …

Abstract CountSketch and Feature Hashing (the``hashing trick'') are popular randomized
dimensionality reduction methods that support recovery of l2-heavy hitters and approximate …

We employ random matrix theory to establish consistency of generalized cross validation
(GCV) for estimating prediction risks of sketched ridge regression ensembles, enabling …