paper-with-me

Papers

CaAdam: Improving Adam optimizer using connection aware methods

2024-10-31 · Remi Genet, Hugo Inzirillo

We introduce a new method inspired by Adam that enhances convergence speed and achieves better loss function minima. Traditional optimizers, including Adam, apply uniform or globally adjusted learning rates across neural networks without considering their architectural specifics. This architecture-agnostic approach is deeply embedded in most deep learning frameworks, where optimizers are implemented as standalone modules without direct access to the network's structural information. For instance, in popular frameworks like Keras or PyTorch, optimizers operate solely on gradients and parameters, without knowledge of layer connectivity or network topology. Our algorithm, CaAdam, explores this overlooked area by introducing connection-aware optimization through carefully designed proxies of architectural information. We propose multiple scaling methodologies that dynamically adjust learning rates based on easily accessible structural properties such as layer depth, connection counts, and gradient distributions. This approach enables more granular optimization while working within the constraints of current deep learning frameworks. Empirical evaluations on standard datasets (e.g., CIFAR-10, Fashion MNIST) show that our method consistently achieves faster convergence and higher accuracy compared to standard Adam optimizer, demonstrating the potential benefits of incorporating architectural awareness in optimization strategies.

📄 PDF Abstract BibTeX arXiv:2410.24216

Code (1)

remigenet/Caadam 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Adam 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling

2024-05-23 · Shuaipeng Li, Penghao Zhao, Hailin Zhang, Xingwu Sun 외

In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters …

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

2024-10-21 · Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during trai…

FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

2024-05-21 · Dongseong Hwang

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis …

Speech Recognition

PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective

2025-05-27 · Tim Tsz-Kit Lau, Qi Long, Weijie Su

The ever-growing scale of deep learning models and datasets underscores the critical importance of efficient optimization methods. While preconditioned gradient methods such as Adam and AdamW are the de facto optimizers …

Language ModelingLanguage Modelling

PDE-aware Optimizer for Physics-informed Neural Networks

2025-07-10 · Vismay Churiwala, Hardik Shukla, Manurag Khullar arxiv

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs) by embedding physical constraints into the loss function. However, standard optimizers such …