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.
Backpropagation and stochastic gradient descent method
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.