activity
20242026
collaborators

6 papers

cs.LG2026

A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms

Gil Goldshlager, Jiang Hu, Lin Lin

Subsampled natural gradient descent (SNG) has been used to enable high-precision scientific machine learning, but standard analyses based on stochastic preconditioning fail to prov…

cs.LG2025

Worth Their Weight: Randomized and Regularized Block Kaczmarz Algorithms without Preprocessing

Gil Goldshlager, Jiang Hu, Lin Lin

Due to the ever growing amounts of data leveraged for machine learning and scientific computing, it is increasingly important to develop algorithms that sample only a small portion…

cs.LG2025

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization

Andrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager +1

Natural gradient methods significantly accelerate the training of Physics-Informed Neural Networks (PINNs), but are often prohibitively costly. We introduce a suite of techniques t…

math.NA2025

Randomized Kaczmarz with tail averaging

Ethan N. Epperly, Gil Goldshlager, Robert J. Webber

The randomized Kaczmarz (RK) method is a well-known approach for solving linear least-squares problems with a large number of rows. RK accesses and processes just one row at a time…

physics.comp-ph2024

A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions

Gil Goldshlager, Nilin Abrahamsen, Lin Lin

Neural network wavefunctions optimized using the variational Monte Carlo method have been shown to produce highly accurate results for the electronic structure of atoms and small m…

cs.LG2024

Convergence of variational Monte Carlo simulation and scale-invariant pre-training

Nilin Abrahamsen, Zhiyan Ding, Gil Goldshlager +1

We provide theoretical convergence bounds for the variational Monte Carlo (VMC) method as applied to optimize neural network wave functions for the electronic structure problem. We…