= Two-point lower bound with a triangular bump
For <fixed-design nonparametric regression>, compare $m_0=0$ with $m_1(x)=L(h-|x-x_0|)_+$. This pair has parameter separation $Lh$ at $x_0$, <Lipschitz bound> $L$, and <Kullback-Leibler divergence> at most $L^2h^2(2nh+1)/(2\sigma^2)$. Choosing $h\asymp(\sigma^2/(nL^2))^{1/3}$ controls <total variation distance> by <Pinsker's inequality> and yields the <pointwise minimax rate for Lipschitz regression> through the <Le Cam two-point lemma>.
Back to article page
