ZO-SAH accelerates zeroth-order optimization by estimating and using subspace Hessians via quadratic fitting with evaluation reuse, achieving faster convergence on logistic regression and neural network benchmarks.
Berahas, Liyuan Cao, Krzysztof Choromanski, and Katya Scheinberg
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
ZO-SAH accelerates zeroth-order optimization by estimating and using subspace Hessians via quadratic fitting with evaluation reuse, achieving faster convergence on logistic regression and neural network benchmarks.