PILOT is a policy-informed learned optimizer that conditions its update on gradient agreement to adapt between momentum, normalization, and sign-based rules, reporting highest accuracies on FashionMNIST and CIFAR-10 with CNN and ResNet-18.
Development of deep learning optimizers: Approaches, concepts, and update rules.arXiv preprint arXiv:2509.18396, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training
PILOT is a policy-informed learned optimizer that conditions its update on gradient agreement to adapt between momentum, normalization, and sign-based rules, reporting highest accuracies on FashionMNIST and CIFAR-10 with CNN and ResNet-18.