Double descent refers to the phase transition that is exhibited by the generalization error of
unregularized learning models when varying the ratio between the number of parameters …

Large matrices arise in many machine learning and data analysis applications, including as
representations of datasets, graphs, model weights, and first and second-order derivatives …

In second-order optimization, a potential bottleneck can be computing the Hessian matrix of
the optimized function at every iteration. Randomized sketching has emerged as a powerful …

Bagging is a commonly used ensemble technique in statistics and machine learning to
improve the performance of prediction procedures. In this paper, we study the prediction risk …

We consider minimizing a smooth and strongly convex objective function using a stochastic
Newton method. At each iteration, the algorithm is given an oracle access to a stochastic …

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 …

It is often desirable to reduce the dimensionality of a large dataset by projecting it onto a low-
dimensional subspace. Matrix sketching has emerged as a powerful technique for …

Determinantal point processes (DPPs) are a useful probabilistic model for selecting a small
diverse subset out of a large collection of items, with applications in summarization …

We propose a randomized algorithm with quadratic convergence rate for convex
optimization problems with a self-concordant, composite, strongly convex objective function …

We propose a new randomized algorithm for solving L2-regularized least-squares problems
based on sketching. We consider two of the most popular random embeddings, namely …