| 大会名称 |
|---|
| 2018年 情報科学技術フォーラム(FIT) |
| 大会コ－ド |
| F |
| 開催年 |
| 2018 |
| 発行日 |
| 2018-09-12 |
| セッション番号 |
| 7f |
| セッション名 |
| 機械学習（５） |
| 講演日 |
| 2018/09/21 |
| 講演場所(会議室等) |
| D棟D23 |
| 講演番号 |
| IF-009 |
| タイトル |
| Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks |
| 著者名 |
| 井田安俊, 藤原靖宏, 岩村相哲, |
| キーワード |
| 深層学習 |
| 抄録 |
|
Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessianbased preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approximation may be inaccurate. In this paper, we propose a novel adaptive learning rate algorithm called SDProp. Its key idea is effective handling of the noise by preconditioning based on covariance matrix. For various neural networks, our approach is more efficient and effective than RMSProp and its variant. |
| 本文pdf |
| PDF download (199.9KB) |