Accelerating matrix factorization by overparameterization

研究成果: 書貢獻/報告類型會議論文篇章同行評審

5 引文 斯高帕斯(Scopus)

摘要

This paper studies overparameterization on the matrix factorization (MF) model. We confirm that overparameterization can significantly accelerate the optimization of MF with no change in the expressiveness of the learning model. Consequently, modern applications on recommendations based on MF or its variants can largely benefit from our discovery. Specifically, we theoretically derive that applying the vanilla stochastic gradient descent (SGD) on the overparameterized MF model is equivalent to employing gradient descent with momentum and adaptive learning rate on the standard MF model. We empirically compare the overparameterized MF model with the standard MF model based on various optimizers, including vanilla SGD, AdaGrad, Adadelta, RMSprop, and Adam, using several public datasets. The experimental results comply with our analysis - overparameterization converges faster. The overparameterization technique can be applied to various learning-based recommendation models, including deep learning-based recommendation models, e.g., SVD++, nonnegative matrix factorization (NMF), factorization machine (FM), NeuralCF, Wide&Deep, and DeepFM. Therefore, we suggest utilizing the overparameterization technique to accelerate the training speed for the learning-based recommendation models whenever possible, especially when the size of the training dataset is large.

原文???core.languages.en_GB???
主出版物標題DeLTA 2020 - Proceedings of the 1st International Conference on Deep Learning Theory and Applications
編輯Ana Fred, Kurosh Madani
發行者SciTePress
頁面89-97
頁數9
ISBN(電子)9789897584411
出版狀態已出版 - 2020
事件1st International Conference on Deep Learning Theory and Applications, DeLTA 2020 - Virtual, Online
持續時間: 8 7月 202010 7月 2020

出版系列

名字DeLTA 2020 - Proceedings of the 1st International Conference on Deep Learning Theory and Applications

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???1st International Conference on Deep Learning Theory and Applications, DeLTA 2020
城市Virtual, Online
期間8/07/2010/07/20

指紋

深入研究「Accelerating matrix factorization by overparameterization」主題。共同形成了獨特的指紋。

引用此