paper-with-me

홈 › Papers

SoftAdam: Unifying SGD and Adam for better stochastic gradient descent

2019-09-25 · Abraham J. Fetterman, Christina H. Kim, Joshua Albrecht

Abstract Stochastic gradient descent (SGD) and Adam are commonly used to optimize deep neural networks, but choosing one usually means making tradeoffs between speed, accuracy and stability. Here we present an intuition for why the tradeoffs exist as well as a method for unifying the two in a continuous way. This makes it possible to control the way models are trained in much greater detail. We show that for default parameters, the new algorithm equals or outperforms SGD and Adam across a range of models for image classification tasks and outperforms SGD for language modeling tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

On Higher-order Moments in Adam

2019-10-15 · Zhanhong Jiang, Aditya Balu, Sin Yong Tan, Young M. Lee 외

In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments. While Adam is an adaptive lower-order moment based (of the stochastic gradient) method, we …

Variational Stochastic Gradient Descent for Deep Neural Networks

2024-04-09 · Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub M Tomczak

Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for…

image-classificationImage ClassificationVariational Inference

Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

2019-05-27 · Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev 외

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, m…

General Classificationimage-classificationLanguage Modelingspeech-recognition+2

Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments

2020-01-01 · ICLR 2020 1 · Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev 외

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, m…

General Classificationimage-classificationImage ClassificationLanguage Modeling+5

Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be

2023-04-27 · Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington, Mark Schmidt

The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy i…