AWhat changed
Maintained separate matrix preconditioners for tensor dimensions to exploit parameter structure, with an online/convex analysis and empirical neural-network optimization comparisons.
Scientific scope
Maintained separate matrix preconditioners for tensor dimensions to exploit parameter structure, with an online/convex analysis and empirical neural-network optimization comparisons. Source convex/online guarantees are not global convergence guarantees for nonconvex deep networks. Per-mode matrix operations carry computation and memory costs; the full proof was not independently audited.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Source convex/online guarantees are not global convergence guarantees for nonconvex deep networks. Per-mode matrix operations carry computation and memory costs; the full proof was not independently audited.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Shampoo: Preconditioned Stochastic Tensor Optimization
- Gupta, Koren and Singer: Shampoo tensor preconditioning — author/proceedings record
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction