Rademacher symmetrization inequality
ID: rademacher-symmetrization-inequality
For an i.i.d. sample and an integrable function class ,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.
New to topics? Read the docs here!