ロード中...
The inverse variance–flatness relation in stochastic gradient descent is critical for finding flat minima
Despite tremendous success of the stochastic gradient descent (SGD) algorithm in deep learning, little is known about how SGD finds generalizable solutions at flat minima of the loss function in high-dimensional weight space. Here, we investigate the connection between SGD learning dynamics and the...
保存先:
| 出版年: | Proc Natl Acad Sci U S A |
|---|---|
| 主要な著者: | , |
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
National Academy of Sciences
2021
|
| 主題: | |
| オンライン･アクセス: | https://ncbi.nlm.nih.gov/pmc/articles/PMC7936325/ https://ncbi.nlm.nih.gov/pubmed/33619091 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1073/pnas.2015617118 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|