PeZO makes zeroth-order learning hardware-friendly by reusing a small pool of uniform random perturbations rescaled to match Gaussian length statistics, achieving accuracy close to MeZO with far fewer random number generators.
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
-
Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
PeZO makes zeroth-order learning hardware-friendly by reusing a small pool of uniform random perturbations rescaled to match Gaussian length statistics, achieving accuracy close to MeZO with far fewer random number generators.