Gaussian Approximation of Quantization Error for Estimation From Compressed Data

DOI10.1109/TIT.2021.3083271MaRDI QIDQ4958248zbMATH OpenFDO

Authors Alon Kipnis, Galen Reeves

Publication date 7 September 2021

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

Full work available at URL https://arxiv.org/abs/2001.03243

zbMATH Keywords

additive white Gaussian noisehigh-dimensional signallossy compressed representationrandom spherical codeWasserstein distance

Mathematics Subject Classification ID

Source coding (94A29)

Abstract: We consider the distributional connection between the lossy compressed representation of a high-dimensional signal $X$ using a random spherical code and the observation of $X$ under an additive white Gaussian noise (AWGN). We show that the Wasserstein distance between a bitrate-$R$ compressed version of $X$ and its observation under an AWGN-channel of signal-to-noise ratio $2^{2R}-1$ is sub-linear in the problem dimension. We utilize this fact to connect the risk of an estimator based on an AWGN-corrupted version of $X$ to the risk attained by the same estimator when fed with its bitrate-$R$ quantized version. We demonstrate the usefulness of this connection by deriving various novel results for inference problems under compression constraints, including minimax estimation, sparse regression, compressed sensing, and the universality of linear estimation in remote source coding.

Recommendations

• The Rate-Distortion Risk in Estimation From Compressed Data
• Low-resolution scalar quantization for Gaussian sources and squared error
• Error Decay of (almost) Consistent Signal Estimations from Quantized Gaussian Random Projections
• Run-length compression of quantized Gaussian stationary signals
• Multidimensional companding quantization of the gaussian source
• Compressive Gaussian mixture estimation
• Threshold Effects in Parameter Estimation From Compressed Data
• scientific article; zbMATH DE number 78504
• Estimation via compressed information
• Low-Resolution Scalar Quantization for Gaussian Sources and Absolute Error

Cited in

(6)

• Quantization with adaptation -- estimation of Gaussian linear models
• Error Decay of (almost) Consistent Signal Estimations from Quantized Gaussian Random Projections
• scientific article; zbMATH DE number 5968919 (Why is no real title available?)
• Error Inhomogeneity in Wavelet-Based Compression
• Compressed and Quantized Correlation Estimators
• The Rate-Distortion Risk in Estimation From Compressed Data

This page was built for publication: Gaussian Approximation of Quantization Error for Estimation From Compressed Data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4958248)