paper-with-me

Papers

Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well

2020-01-07 · ICLR 2020 1 · Vipul Gupta, Santiago Akle Serrano, Dennis Decoste

We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training. Our algorithm uses large mini-batches to compute an approximate solution quickly and then refines it by averaging the weights of multiple models computed independently and in parallel. The resulting models generalize equally well as those trained with small mini-batches but are produced in a substantially shorter time. We demonstrate the reduction in training time and the good generalization performance of the resulting models on the computer vision datasets CIFAR10, CIFAR100, and ImageNet.

📄 PDF Abstract BibTeX arXiv:2001.02312

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

Similar Papers 제목 키워드 기반

Parallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecification

2016-10-12 · Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli 외

This work characterizes the benefits of averaging schemes widely used in conjunction with stochastic gradient descent (SGD). In particular, this work provides a sharp analysis of: (1) mini-batching, a method of averaging…

regression

Parallel Dither and Dropout for Regularising Deep Neural Networks

2015-08-28 · Andrew J. R. Simpson

Effective regularisation during training can mean the difference between success and failure for deep neural networks. Recently, dither has been suggested as alternative to dropout for regularisation during batch-average…

Behavior of Mini-Batch Optimization for Training Deep Neural Networks on Large Datasets

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

Stochastic Weight Averaging in Parallel (SWAP) is a method that enables the training of deep neural networks on large datasets using large mini-batch sizes while also not sacrificing good generalization behavior. The alg…

image-classificationImage Classification

Experiments on Parallel Training of Deep Neural Network using Model Averaging

2015-07-05 · Hang Su, Haoyu Chen

In this work we apply model averaging to parallel training of deep neural network (DNN). Parallelization is done in a model averaging manner. Data is partitioned and distributed to different nodes for local model updates…

DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging

2020-05-31 · Qinggang Zhou, Yawen Zhang, Pengcheng Li, Xiaoyong Liu 외

The state-of-the-art deep learning algorithms rely on distributed training systems to tackle the increasing sizes of models and training data sets. Minibatch stochastic gradient descent (SGD) algorithm requires workers t…