AdaFisher replaces Adam's second-moment estimate with a diagonal Kronecker-factored Fisher preconditioner, reporting higher accuracy and lower perplexity than Adam, K-FAC, Shampoo, and AdaHessian at comparable wall-clock cost.
A second-order-like optimizer with adaptive gradient scaling for deep learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this empirical article, we introduce INNAprop, an optimization algorithm that combines the INNA method with the RMSprop adaptive gradient scaling. It leverages second-order information and rescaling while keeping the memory requirements of standard DL methods as AdamW or SGD with momentum. After giving geometrical insights, we evaluate INNAprop on CIFAR-10, Food101, and ImageNet with ResNets, VGG, DenseNet, and ViT, and on GPT-2 (OpenWebText) train from scratch and with LoRA fine-tuning (E2E). INNAprop consistently matches or outperforms AdamW both in training speed and accuracy, with minimal hyperparameter tuning in large-scale settings. Our code is publicly available at \url{https://github.com/innaprop/innaprop}.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis
AdaFisher replaces Adam's second-moment estimate with a diagonal Kronecker-factored Fisher preconditioner, reporting higher accuracy and lower perplexity than Adam, K-FAC, Shampoo, and AdaHessian at comparable wall-clock cost.