Lower bounds for the minimax risk using f-divergences and applications

2010/01/30 by Adityanand Guntuboyina, Guntuboyina, Adityanand
Mathematics · #FOS: Mathematics #Statistics Theory (math.ST) #math.ST #stat.TH

paper · pdf · doi:10.48550/arxiv.1002.0042

arxiv created 2011/02/18 · arxiv updated 2011/02/22

Abstract

Lower bounds involving f-divergences between the underlying probability measures are proved for the minimax risk in estimation problems. Our proofs just use simple convexity facts. Special cases and straightforward corollaries of our bounds include well known inequalities for establishing minimax lower bounds such as Fano's inequality, Pinsker's inequality and inequalities based on global entropy conditions. Two applications are provided: a new minimax lower bound for the reconstruction of convex bodies from noisy support function measurements and a different proof of a recent minimax lower bound for the estimation of a covariance matrix.

Related

• High-probability minimax lower bounds
• Lower-bounds on the Bayesian Risk in Estimation Procedures via f-Divergences
• Minimax estimation of norms of a probability density: I. Lower bounds
• On Bayes Risk Lower Bounds
• Revisiting Le Cam's Equation: Exact Minimax Rates over Convex Density Classes