Pith. sign in

Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Adaptive optimizers are pivotal in guiding the weight updates of deep neural networks, yet they often face challenges such as poor generalization and oscillation issues. To counter these, we introduce sigSignGrad and tanhSignGrad, two novel optimizers that integrate adaptive friction coefficients based on the Sigmoid and Tanh functions, respectively. These algorithms leverage short-term gradient information, a feature overlooked in traditional Adam variants like diffGrad and AngularGrad, to enhance parameter updates and convergence.Our theoretical analysis demonstrates the wide-ranging adjustment capability of the friction coefficient S, which aligns with targeted parameter update strategies and outperforms existing methods in both optimization trajectory smoothness and convergence rate. Extensive experiments on CIFAR-10, CIFAR-100, and Mini-ImageNet datasets using ResNet50 and ViT architectures confirm the superior performance of our proposed optimizers, showcasing improved accuracy and reduced training time. The innovative approach of integrating adaptive friction coefficients as plug-ins into existing optimizers, exemplified by the sigSignAdamW and sigSignAdamP variants, presents a promising strategy for boosting the optimization performance of established algorithms. The findings of this study contribute to the advancement of optimizer design in deep learning.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2024 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

Few-Shot Learning with Adaptive Weight Masking in Conditional GANs

cs.CV · 2024-12-04 · reject · novelty 2.0

A CGAN with residual generator blocks and a heuristically computed weight mask on the discriminator reports better IS/FID on MNIST, but the paper lacks downstream few-shot evaluation and any code or training details.

citing papers explorer

Showing 1 of 1 citing paper.

  • Few-Shot Learning with Adaptive Weight Masking in Conditional GANs cs.CV · 2024-12-04 · reject · none · ref 11 · internal anchor

    A CGAN with residual generator blocks and a heuristically computed weight mask on the discriminator reports better IS/FID on MNIST, but the paper lacks downstream few-shot evaluation and any code or training details.