3 papers
cs.LG2026
Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage
Alan Milligan, Zikun Xu, Simon Lacoste-Julien +2
Shampoo-based methods, such as KL-Shampoo and SOAP, have demonstrated strong performance in training neural networks and rely on QR decomposition. Because existing QR implementatio…
physics.flu-dyn2026
Long-time turbulence prediction at fine time steps using multi-stride neural operators
Guanyu Pan, Huiyu Yang, Yunpeng Wang +3
Long-time turbulence prediction at fine time steps is costly and prone to error accumulation, while accurate short-term fields do not ensure accurate long-time statistics. We propo…
stat.ML2025
Understanding and Improving Shampoo and SOAP via Kullback-Leibler Minimization
Wu Lin, Scott C. Lowe, Felix Dangel +3
Shampoo and its efficient variant, SOAP, employ structured second-moment estimations and have shown strong performance for training neural networks (NNs). In practice, however, Sha…