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

Chernoff bound #3

Closed
delta2323 opened this issue Jun 9, 2018 · 0 comments
Closed

Chernoff bound #3

delta2323 opened this issue Jun 9, 2018 · 0 comments

Comments

@delta2323
Copy link
Owner

delta2323 commented Jun 9, 2018

ステートメント

$X$を確率変数とする,任意の$t>0$と$\lambda \in \mathbb{R}$に対して
$$
\mathbb{P}\{ |X - \mathbb{E}X| \geq t\} \leq e^{\psi_{X}(\lambda)-\lambda t}.
$$
ここで,$\psi_{X}$は$X$の生成母関数の対数,$\psi_{X}(\lambda):=\log \mathbb{E}\left[e^{\lambda X} \right]$.

証明の概要

Markovの不等式(#1)から証明できる

コメント

この不等式により,期待値周りの確率集中は生成母関数の対数$\psi_X$を評価することに帰着される

出典

Boucheron et al. Concentration inequalities: A Nonasymptotic Theory of Independence (2013)

@delta2323 delta2323 changed the title 指数型Chebyshevの不等式 Chernoff bound Jun 13, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant