Quantizing heavy-tailed data in statistical estimation: (near) minimax rates, covariate quantization, and uniform recovery

DOI10.1109/TIT.2023.3329240MaRDI QIDQ6576109zbMATH OpenFDO

Authors Michael Ng, Di Wang

Publication date 22 July 2024

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

Full work available at URL https://doi.org/10.1109/TIT.2023.3329240

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20)

Cited in

(4)

• Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors
• Tensor recovery from quantized measurements based on modewise operators
• A parameter-free two-bit covariance estimator with improved operator norm error rate
• Robust tensor completion from uniformly dithered one-bit observations

This page was built for publication: Quantizing heavy-tailed data in statistical estimation: (near) minimax rates, covariate quantization, and uniform recovery

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6576109)