1 citations · 1 across the 7 of their papers we have counts for
8 papers
Does block size matter in randomized block Krylov low-rank approximation?
Tyler Chen, Ethan N. Epperly, Raphael A. Meyer +2
We study the problem of computing a rank- approximation of a matrix using randomized block Krylov iteration. Prior work has shown that, for block size or , a $(1…
Algorithm-agnostic low-rank approximation of operator monotone matrix functions
David Persson, Raphael A. Meyer, Christopher Musco
Low-rank approximation of a matrix function, , is an important task in computational mathematics. Most methods require direct access to , which is often considerably mo…
On the Unreasonable Effectiveness of Single Vector Krylov Methods for Low-Rank Approximation
Raphael A. Meyer, Cameron Musco, Christopher Musco
Krylov subspace methods are a ubiquitous tool for computing near-optimal rank approximations of large matrices. While "large block" Krylov methods with block size at least …
Near-Linear Sample Complexity for Polynomial Regression
Raphael A. Meyer, Cameron Musco, Christopher Musco +2
We study polynomial regression. Given query access to a function , the goal is to find a degree polynomial such that, for a giv…
Fast Regression for Structured Inputs
Raphael A. Meyer, Cameron Musco, Christopher Musco +2
We study the regression problem, which requires finding that minimizes for a matrix $\mathbf{A}\in\mat…
Hutch++: Optimal Stochastic Trace Estimation
Raphael A. Meyer, Cameron Musco, Christopher Musco +1
We study the problem of estimating the trace of a matrix that can only be accessed through matrix-vector multiplication. We introduce a new randomized algorithm, Hutch++, which…
The Statistical Cost of Robust Kernel Hyperparameter Tuning
Raphael A. Meyer, Christopher Musco
This paper studies the statistical complexity of kernel hyperparameter tuning in the setting of active regression under adversarial noise. We consider the problem of finding the be…
Optimality Implies Kernel Sum Classifiers are Statistically Efficient
Raphael Arkady Meyer, Jean Honorio
We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typ…