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

SEVER: A Robust Meta-Algorithm for Stochastic Optimization #8

Open
nocotan opened this issue Dec 31, 2020 · 0 comments
Open

SEVER: A Robust Meta-Algorithm for Stochastic Optimization #8

nocotan opened this issue Dec 31, 2020 · 0 comments

Comments

@nocotan
Copy link
Member

nocotan commented Dec 31, 2020

一言でいうと

外れ値に頑健な確率的最適化のためのメタアルゴリズムを提案.

論文リンク

ICML2019
http://proceedings.mlr.press/v97/diakonikolas19a.html

著者/所属機関

Ilias Diakonikolas (University of California), Gautam Kamath (University of California), Daniel M. Kane, Jerry Li (Microsoft Research AI), Jacob Steinhardt (University of California), Alistair Stewart (Web3 Foundation)

投稿日付(yyyy/MM/dd)

2018/03/07

概要

外れ値に頑健な確率的最適化のためのメタアルゴリズムであるSEVERを提案:

  • 高次元な入力であっても任意の外れ値を扱うことが可能
  • 回帰や分類,ニューラルネットワークを含む非凸最適化など一般的な学習問題に広く適用可能
  • 一般的な機械学習ライブラリで容易に実装可能

新規性・差分

既存手法は高次元な場合に適用が難しかったが,提案手法は高次元な場合に適用可能.

手法

Screen Shot 2021-01-01 at 4 07 06

Screen Shot 2021-01-01 at 4 07 27

結果

Screen Shot 2021-01-01 at 4 07 49

Screen Shot 2021-01-01 at 4 08 13

コメント

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