A benchmark plus a variance bound showing structured orthogonal direction matrices improve gradient estimation and convergence in finite-difference optimization with little extra generation cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Structured Tour of Optimization with Finite Differences
A benchmark plus a variance bound showing structured orthogonal direction matrices improve gradient estimation and convergence in finite-difference optimization with little extra generation cost.