Runa Eschenhagen

Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner

Influence Functions for Scalable Data Attribution in Diffusion Models

Accelerating neural network training: An analysis of the AlgoPerf competition

Fast Fractional Natural Gradient Descent using Learnable Spectral Factorizations