A locality-aware surrogate loss derived from the gradient theorem improves gradient estimation and query efficiency in black-box optimization.
Single-shot optical neural network
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
-
Locality-aware Surrogates for Gradient-based Black-box Optimization
A locality-aware surrogate loss derived from the gradient theorem improves gradient estimation and query efficiency in black-box optimization.