Minimax Estimation of the <inline-formula> <tex-math notation="LaTeX">L_{1} </tex-math> </inline-formula> Distance

DOI10.1109/TIT.2018.2846245MaRDI QIDQ4682944zbMATH OpenFDO

Authors Jiantao Jiao, Yanjun Han, Tsachy Weissman

Publication date 19 September 2018

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1705.00807

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: We consider the problem of estimating the $L_1$ distance between two discrete probability measures $P$ and $Q$ from empirical data in a nonasymptotic and large alphabet setting. When $Q$ is known and one obtains $n$ samples from $P$, we show that for every $Q$, the minimax rate-optimal estimator with $n$ samples achieves performance comparable to that of the maximum likelihood estimator (MLE) with $nlnn$ samples. When both $P$ and $Q$ are unknown, we construct minimax rate-optimal estimators whose worst case performance is essentially that of the known $Q$ case with $Q$ being uniform, implying that $Q$ being uniform is essentially the most difficult case. The emph{effective sample size enlargement} phenomenon, identified in Jiao emph{et al.} (2015), holds both in the known $Q$ case for every $Q$ and the $Q$ unknown case. However, the construction of optimal estimators for $|P-Q{|}_1$ requires new techniques and insights beyond the approximation-based method of functional estimation in Jiao emph{et al.} (2015).

Cited in

(20)

• Upper bounds for the \(L_ 1\)-risk of the minimum \(L_ 1\)-distance regression estimator
• Hypothesis testing for high-dimensional multinomials: a selective review
• Optimal rates of entropy estimation over Lipschitz balls
• Minimum distance estimation in normed linear spaces with Donsker-classes
• Expected value of the one-dimensional earth mover's distance
• Estimation of Wasserstein distances in the spiked transport model
• On minimum Hellinger distance estimation
• A General Approach to the Optimality of Minimum Distance Estimators
• Approximate profile maximum likelihood
• Efficient minimum distance estimation with multiple rates of convergence
• Optimal Estimation of Wasserstein Distance on a Tree With an Application to Microbiome Studies
• Higher‐order asymptotics of minimax estimators for time series
• Fisher-Pitman Permutation Tests Based on Nonparametric Poisson Mixtures with Application to Single Cell Genomics
• Optimal nonparametric testing of missing completely at random and its connections to compatibility
• Tests of missing completely at random based on sample covariance matrices
• Mixing time estimation in ergodic Markov chains from a single trajectory with contraction methods
• Testing product distributions: a closer look
• Sharp convergence rates of empirical unbalanced optimal transport for spatio-temporal point processes
• Approximate independence of permutation mixtures
• Estimation and inference for the Wasserstein distance between mixing measures in topic models

This page was built for publication: Minimax Estimation of the <inline-formula> <tex-math notation="LaTeX">$L_{1}$ </tex-math> </inline-formula> Distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4682944)