AdaFisher replaces Adam's second-moment estimate with a diagonal Kronecker-factored Fisher preconditioner, reporting higher accuracy and lower perplexity than Adam, K-FAC, Shampoo, and AdaHessian at comparable wall-clock cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis
AdaFisher replaces Adam's second-moment estimate with a diagonal Kronecker-factored Fisher preconditioner, reporting higher accuracy and lower perplexity than Adam, K-FAC, Shampoo, and AdaHessian at comparable wall-clock cost.