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

• URL: http://arxiv.org/abs/2001.02312v1
• Date: Tue, 7 Jan 2020 23:13:35 GMT
• Title: Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well
• Authors: Vipul Gupta, Santiago Akle Serrano, Dennis DeCoste
• Abstract summary: We propose Weight Averaging in Parallel (SWAP) 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.
• Score: 7.262048441360133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Always-Sparse Training by Growing Connections with Guided Stochastic Exploration [46.4179239171213]
  We propose an efficient always-sparse training algorithm with excellent scaling to larger and sparser models. We evaluate our method on CIFAR-10/100 and ImageNet using VGG, and ViT models, and compare it against a range of sparsification methods.
  arXiv  Detail & Related papers  (2024-01-12T21:32:04Z)
• SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient [69.61083127540776]
  Deep learning applications benefit from using large models with billions of parameters. Training these models is notoriously expensive due to the need for specialized HPC clusters. We consider alternative setups for training large models: using cheap "preemptible" instances or pooling existing resources from multiple regions.
  arXiv  Detail & Related papers  (2023-01-27T18:55:19Z)
• FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level [7.410940271545853]
  We present FastHebb, an efficient and scalable solution for Hebbian learning. FastHebb outperforms previous solutions by up to 50 times in terms of training speed. For the first time, we are able to bring Hebbian algorithms to ImageNet scale.
  arXiv  Detail & Related papers  (2022-07-07T09:04:55Z)
• PFGE: Parsimonious Fast Geometric Ensembling of DNNs [6.973476713852153]
  In this paper, we propose a new method called parsimonious FGE (PFGE), which employs a lightweight ensemble of higher-performing deep neural networks. Our results show PFGE 5x memory efficiency compared to previous methods, without compromising on generalization performance.
  arXiv  Detail & Related papers  (2022-02-14T12:27:46Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Training Sparse Neural Networks using Compressed Sensing [13.84396596420605]
  We develop and test a novel method based on compressed sensing which combines the pruning and training into a single step. Specifically, we utilize an adaptively weighted $ell1$ penalty on the weights during training, which we combine with a generalization of the regularized dual averaging (RDA) algorithm in order to train sparse neural networks.
  arXiv  Detail & Related papers  (2020-08-21T19:35:54Z)
• Automatic Cross-Replica Sharding of Weight Update in Data-Parallel Training [12.36664837965624]
  This paper presents an approach to automatically shard the weight update across replicas. We show this technique achieves substantial speedups on typical image and language models on Cloud TPUs.
  arXiv  Detail & Related papers  (2020-04-28T07:13:50Z)
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits [99.59941892183454]
  We propose Einsum Networks (EiNets), a novel implementation design for PCs. At their core, EiNets combine a large number of arithmetic operations in a single monolithic einsum-operation. We show that the implementation of Expectation-Maximization (EM) can be simplified for PCs, by leveraging automatic differentiation.
  arXiv  Detail & Related papers  (2020-04-13T23:09:15Z)
• Learning Gaussian Graphical Models via Multiplicative Weights [54.252053139374205]
  We adapt an algorithm of Klivans and Meka based on the method of multiplicative weight updates. The algorithm enjoys a sample complexity bound that is qualitatively similar to others in the literature. It has a low runtime $O(mp2)$ in the case of $m$ samples and $p$ nodes, and can trivially be implemented in an online manner.
  arXiv  Detail & Related papers  (2020-02-20T10:50:58Z)
• Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving [106.63673243937492]
  Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning. We frame the task of feedforward computation as solving a system of nonlinear equations. We then propose to find the solution using a Jacobi or Gauss-Seidel fixed-point method, as well as hybrid methods of both. Our method is guaranteed to give exactly the same values as the original feedforward computation with a reduced (or equal) number of parallelizable iterations, and hence reduced time given sufficient parallel computing power.
  arXiv  Detail & Related papers  (2020-02-10T10:11:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.