The authors show that when unperturbed neural network training reaches a quasi-steady state, the mean time to a target test accuracy under periodic perturbations can be predicted from a single perturbation experiment.
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
-
First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models
The authors show that when unperturbed neural network training reaches a quasi-steady state, the mean time to a target test accuracy under periodic perturbations can be predicted from a single perturbation experiment.