Skip to main content
← Choose a different target

Unlock: Preconditioned Optimizers: Shampoo, K-FAC, and Natural Gradient

Optimizers that use curvature information to precondition gradients: the natural gradient via Fisher information, K-FAC's Kronecker approximation, and Shampoo's full-matrix preconditioning. How they connect to Riemannian optimization and why they outperform Adam on certain architectures.

56 Prerequisites0 Mastered0 Working53 Gaps
Prerequisite mastery5%
Recommended probe

Borel-Cantelli Lemmas is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.

Preconditioned Optimizers: Shampoo, K-FAC, and Natural GradientTARGET
Borel-Cantelli LemmasInfrastructureWEAKEST
Not assessed6 questions
Joint, Marginal, and Conditional DistributionsAxioms
Not assessed30 questions
Cardinality and CountabilityAxioms
Not assessed16 questions
Moment Generating FunctionsAxioms
Not assessed6 questions
Triangular DistributionAxioms
Not assessed4 questions
Zermelo-Fraenkel Set TheoryAxioms
Not assessed5 questions
Convex Optimization BasicsFoundations
Not assessed32 questions
Fisher Information: Curvature, KL Geometry, and the Natural GradientInfrastructure
Not assessed19 questions
The Hessian MatrixAxioms
Not assessed16 questions
Conjugate Gradient MethodsCore
Not assessed2 questions

Sign in to track your mastery and see personalized gap analysis.