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

Stochastic gradient descent on Riemannian manifolds #21

Open
nocotan opened this issue Jan 13, 2021 · 0 comments
Open

Stochastic gradient descent on Riemannian manifolds #21

nocotan opened this issue Jan 13, 2021 · 0 comments

Comments

@nocotan
Copy link
Member

nocotan commented Jan 13, 2021

一言でいうと

確率的勾配降下法をリーマン多様体の上で定義された関数に拡張.

論文リンク

https://arxiv.org/pdf/1111.5280.pdf

著者/所属機関

S. Bonnabel (Mines ParisTech)

投稿日付(yyyy/MM/dd)

2013/11/19

概要

機械学習の中でも重要なタスクとして,行列の低ランク近似がある.

Screen Shot 2021-01-13 at 15 14 31

元の行列が非常に高次元の時,この操作をユークリッド空間で行うのが難しいという問題がある.
この問題について,パラメータ空間をリーマン計量のもとに制限することで解決できる.

Screen Shot 2021-01-13 at 15 11 02

新規性・差分

  • リーマン多様体の上での確率的勾配降下法を定式化
  • 収束性を証明

手法

導出される更新則:
Screen Shot 2021-01-13 at 15 18 37

収束性に関する定理:
Screen Shot 2021-01-13 at 15 19 34

結果

Screen Shot 2021-01-13 at 15 11 28

Screen Shot 2021-01-13 at 15 11 45

Screen Shot 2021-01-13 at 15 12 02

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