paper-with-me

Papers

A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range

2022-03-24 · Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

We make contributions towards improving adaptive-optimizer performance. Our improvements are based on suppression of the range of adaptive stepsizes in the AdaBelief optimizer. Firstly, we show that the particular placement of the parameter epsilon within the update expressions of AdaBelief reduces the range of the adaptive stepsizes, making AdaBelief closer to SGD with momentum. Secondly, we extend AdaBelief by further suppressing the range of the adaptive stepsizes. To achieve the above goal, we perform mutual layerwise vector projections between the gradient g_t and its first momentum m_t before using them to estimate the second momentum. The new optimization method is referred to as Aida. Thirdly, extensive experimental results show that Aida outperforms nine optimizers when training transformers and LSTMs for NLP, and VGG and ResNet for image classification over CIAF10 and CIFAR100 while matching the best performance of the nine methods when training WGAN-GP models for image generation tasks. Furthermore, Aida produces higher validation accuracies than AdaBelief for training ResNet18 over ImageNet. Code is available <a href="https://github.com/guoqiang-x-zhang/AidaOptimizer">at this URL</a>

📄 PDF Abstract BibTeX arXiv:2203.13273

Code (1)

guoqiang-x-zhang/AidaOptimizer 공식 구현 pytorch

Tasks

image-classificationImage ClassificationImage Generation

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Batch Normalization 설명 없음
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients

2020-10-15 · NeurIPS 2020 12 · Juntang Zhuang, Tommy Tang, Yifan Ding, Sekhar Tatikonda 외

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional n…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

AdaBelief Optimizer: Adapting Stepsizes by theBelief in Observed Gradients

2020-10-19 · NeurIPS Workshop DL-IG 2020 12 · Juntang Zhuang, Tommy Tang, Sekhar Tatikonda, Nicha C Dvornek 외

Optimization is at the core of modern deep learning. We propose AdaBelief optimizer to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and training stability. T…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+1

A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning

2022-06-04 · Kushal Chakrabarti, Nikhil Chopra

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorith…

BIG-bench Machine Learningimage-classificationImage ClassificationLanguage Modeling+1

AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs

2022-10-12 · Shiv Ram Dubey, Satish Kumar Singh, Bidyut Baran Chaudhuri

The stochastic gradient descent (SGD) optimizers are generally used to train the convolutional neural networks (CNNs). In recent years, several adaptive momentum based SGD optimizers have been introduced, such as Adam, d…

Object Recognition

FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity

2021-04-28 · Yangfan Zhou, Kaizhu Huang, Cheng Cheng, Xuguang Wang 외

AdaBelief, one of the current best optimizers, demonstrates superior generalization ability compared to the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretical…

Image ClassificationLanguage Modelling