Papers › A second-order-like optimizer with adaptive gradient scaling for deep learning

A second-order-like optimizer with adaptive gradient scaling for deep learning

8 Oct 2024arXiv:2410.05871archive 2025-07-28

Jérôme Bolte, Ryan Boustany, Edouard Pauwels, Andrei Purica

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}.

PaperPDFCode

Code

innaprop/innaprop officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamAdamWAttentionAttention DropoutAverage PoolingBPEBatch NormalizationConcatenated Skip ConnectionConvolutionCosine AnnealingDense BlockDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Global Average PoolingKaiming InitializationLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMax PoolingMulti-Head AttentionRMSPropReLUResidual ConnectionSGDSPEEDSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections