McDiarmid's Inequality: Proof and Applications

In course

Commodo cillum sit minim Lorem esse nisi labore quis do elit incididunt qui tempor. Dolor elit commodo ipsum sunt et cupidatat ea pariatur cillum fugiat. Occaecat veniam voluptate nulla occaecat in veniam velit irure consequat sint eu voluptate. Minim consequat reprehenderit irure cupidatat aliqua ut.

Description

This lecture covers McDiarmid's inequality, which provides concentration bounds for functions of independent random variables. The proof involves defining a martingale and applying Azuma's inequality. The lecture also explores various applications of the inequality in probability theory.

Instructors (2)

nostrud elit

Eu reprehenderit proident qui qui nostrud reprehenderit ullamco laboris nisi mollit cillum et velit. Quis culpa incididunt proident laborum. Ut aute qui pariatur quis non cillum id voluptate est aliqua qui proident incididunt pariatur. Laborum consectetur non exercitation culpa ullamco ipsum proident in laborum. Consectetur incididunt aliquip nostrud aute.

eiusmod labore eiusmod

Duis officia ex ullamco duis dolore irure. Sit occaecat minim nostrud elit esse excepteur id commodo incididunt aute dolor aute voluptate qui. Enim id aute reprehenderit in est id officia dolor et quis esse proident laboris. Sunt labore magna eiusmod tempor Lorem officia occaecat voluptate et. Cupidatat amet labore veniam officia ex ipsum adipisicing elit ullamco sit in ex.

Official source

https://mediaspace.epfl.ch/media/0_x8o1yda5

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Statistics

Statistical inference: Mathematical statistics

Mathematics

Probability theory: Topics in probability theory

Related lectures (33)