112 citations · 119 across the 9 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.LG2024
Curvature-Informed SGD via General Purpose Lie-Group Preconditioners
Omead Pooladzandi, Xi-Lin Li
We present a novel approach to accelerate stochastic gradient descent (SGD) by utilizing curvature information obtained from Hessian-vector products or finite differences of parame…
stat.ML2024
Stochastic Hessian Fittings with Lie Groups
Xi-Lin Li
This report investigates the fitting of the Hessian or its inverse for stochastic optimizations using a Hessian fitting criterion derived from the preconditioned stochastic gradien…