paper-with-me

홈 › Papers

SWALP : Stochastic Weight Averaging in Low-Precision Training

2019-04-26 · Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa

Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precision SGD even with all numbers quantized down to 8 bits, including the gradient accumulators. Additionally, we show that SWALP converges arbitrarily close to the optimal solution for quadratic objectives, and to a noise ball asymptotically smaller than low precision SGD in strongly convex settings.

📄 PDF Abstract BibTeX arXiv:1904.11943

Code (3)

stevenygd/SWALP 공식 구현 pytorch
RICE-EIC/Early-Bird-Tickets pytorch
gatech-eic/early-bird-tickets pytorch

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…

Similar Papers 제목 키워드 기반

SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks

2020-02-02 · Sungho Shin, Yoonho Boo, Wonyong Sung

Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generaliza…

Quantization

Precision-Weighted Federated Learning

2021-07-20 · Jonatan Reyes, Lisa Di Jorio, Cecile Low-Kam, Marta Kersten-Oertel

Federated Learning using the Federated Averaging algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessib…

Computational EfficiencyFederated Learningimage-classificationImage Classification

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 we…

Regularizing Neural Networks by Stochastically Training Layer Ensembles

2019-11-21 · Alex Labach, Shahrokh Valaee

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance t…

General Classificationimage-classificationImage Classification

Iterate averaging as regularization for stochastic gradient descent

2018-02-22 · Gergely Neu, Lorenzo Rosasco

We propose and analyze a variant of the classic Polyak-Ruppert averaging scheme, broadly used in stochastic gradient methods. Rather than a uniform average of the iterates, we consider a weighted average, with weights de…

regression