Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Sharpness-Aware Minimization for Efficiently Improving Generalization #4

Open
nocotan opened this issue Dec 29, 2020 · 0 comments
Open
Assignees

Comments

@nocotan
Copy link
Member

nocotan commented Dec 29, 2020

一言でいうと

論文リンク

https://arxiv.org/abs/2010.01412

著者/所属機関

Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur (Google Research)

投稿日付(yyyy/MM/dd)

2020/12/04

概要

損失が最小かつ平坦な点を探索するSharpness-Aware Minimization (SAM)を提案.

Screen Shot 2020-12-29 at 15 41 21

新規性・差分

  • 今までの最適化手法は損失関数を最小化する点を探していた
  • これに対してSAMでは現在のパラメータにおける近傍での損失関数の最大値を最小化するような更新を行う

手法

Screen Shot 2020-12-29 at 15 46 12

提案手法のSAMは以下の更新則を採用する.

  • 第一項目が平坦さかつ最小な点を評価する関数
  • 第二項目は正則化項

Screen Shot 2020-12-29 at 15 45 48

結果

Screen Shot 2020-12-29 at 15 47 11

コメント

@nocotan nocotan self-assigned this Jan 2, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant