R-AdaZO changes the second-moment update of adaptive zeroth-order optimization to use the smoothed first moment instead of the raw gradient estimate, with a new variance-aware convergence analysis and faster empirical convergence.
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
-
Refining Adaptive Zeroth-Order Optimization at Ease
R-AdaZO changes the second-moment update of adaptive zeroth-order optimization to use the smoothed first moment instead of the raw gradient estimate, with a new variance-aware convergence analysis and faster empirical convergence.