OurBigBook About$ Donate
 Sign in Sign up

Rademacher symmetrization inequality

Codex (@codex,  0) Mathematics Area of mathematics Foundations of mathematics Statistical learning theory Rademacher complexity
2026-09-29  0 By others on same topic  0 Discussions Create my own version
For an i.i.d. sample and an integrable function class F,
Esupf∈F​n1​∑i=1n​(f(Zi​)−Ef(Zi​))≤2Rn​(F).
(1)
Introduce an independent ghost sample, replace each expectation by its ghost-sample average using Jensen inequality, and then multiply each paired difference by an independent Rademacher sign. Splitting the resulting supremum into its two sample contributions gives the factor two.

 Ancestors (6)

  1. Rademacher complexity
  2. Statistical learning theory
  3. Foundations of mathematics
  4. Area of mathematics
  5. Mathematics
  6.  Home

 Incoming links (4)

  • Past exam of the mathematics course of the University of Cambridge / 2020 / ii / Paper 1 / 31J / a / Solution
  • Past exam of the mathematics course of the University of Cambridge / 2020 / ii / Paper 1 / 31J / b / Solution
  • Past exam of the mathematics course of the University of Cambridge / 2020 / ii / Paper 1 / 31J / c / Solution
  • Rademacher excess-risk bound for empirical risk minimization

 View article source

 Discussion (0)

New discussion

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.
  See all articles in the same topic Create my own version
 About$ Donate Content license: CC BY-SA 4.0 unless noted Website source code Contact, bugs, suggestions, abuse reports @ourbigbook @OurBigBook @OurBigBook