Search Results for author: Robert J. Webber

Found 6 papers, 3 papers with code

Robust, randomized preconditioning for kernel ridge regression

1 code implementation24 Apr 2023 Mateo Díaz, Ethan N. Epperly, Zachary Frangella, Joel A. Tropp, Robert J. Webber

This paper introduces two randomized preconditioning techniques for robustly solving kernel ridge regression (KRR) problems with a medium to large number of data points ($10^4 \leq N \leq 10^7$).

regression

Understanding and eliminating spurious modes in variational Monte Carlo using collective variables

no code implementations11 Nov 2022 huan zhang, Robert J. Webber, Michael Lindsey, Timothy C. Berkelbach, Jonathan Weare

The use of neural network parametrizations to represent the ground state in variational Monte Carlo (VMC) calculations has generated intense interest in recent years.

Variational Monte Carlo

Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations

1 code implementation13 Jul 2022 Yifan Chen, Ethan N. Epperly, Joel A. Tropp, Robert J. Webber

The randomly pivoted partial Cholesky algorithm (RPCholesky) computes a factorized rank-k approximation of an N x N positive-semidefinite (psd) matrix.

Rayleigh-Gauss-Newton optimization with enhanced sampling for variational Monte Carlo

no code implementations19 Jun 2021 Robert J. Webber, Michael Lindsey

Second, in order to realize this favorable comparison in the presence of stochastic noise, we analyze the effect of sampling error on VMC parameter updates and experimentally demonstrate that it can be reduced by the parallel tempering method.

Variational Monte Carlo

Learning forecasts of rare stratospheric transitions from short simulations

no code implementations15 Feb 2021 Justin Finkel, Robert J. Webber, Dorian S. Abbot, Edwin P. Gerber, Jonathan Weare

We compute the probability and lead time efficiently by solving equations involving the transition operator, which encodes all information about the dynamics.

Atmospheric and Oceanic Physics Dynamical Systems Data Analysis, Statistics and Probability

A splitting method to reduce MCMC variance

2 code implementations27 Nov 2020 Robert J. Webber, David Aristoff, Gideon Simpson

We explore whether splitting and killing methods can improve the accuracy of Markov chain Monte Carlo (MCMC) estimates of rare event probabilities, and we make three contributions.

Numerical Analysis Numerical Analysis 65C05, 65C40, 82C80

Cannot find the paper you are looking for? You can Submit a new open access paper.