000256573 001__ 256573
000256573 005__ 20190820211009.0
000256573 037__ $$aBOOK_CHAP
000256573 245__ $$aAn Introductory Guide to Fano's Inequality with Applications in Statistical Estimation
000256573 260__ $$bCambridge University Press$$c2019-06-12
000256573 269__ $$a2019-06-12
000256573 336__ $$aBook Chapters
000256573 520__ $$aInformation theory plays an indispensable role in the development of algorithm-independent impossibility results, both for communication problems and for seemingly distinct areas such as statistics and machine learning. While numerous information-theoretic tools have been proposed for this purpose, the oldest one remains arguably the most versatile and widespread: Fano's inequality. In this chapter, we provide a survey of Fano's inequality and its variants in the context of statistical estimation, adopting a versatile framework that covers a wide range of specic problems. We present a variety of key tools and techniques used for establishing impossibility results via this approach, and provide representative examples covering group testing, graphical model selection, sparse linear regression, density estimation, and convex optimization.
000256573 700__ $$aScarlett, Jonathan$$0248483$$g248798
000256573 710__ $$aCevher, Volkan
000256573 773__ $$tInformation-Theoretic Methods in Data Science
000256573 8560_ $$fgosia.baltaian@epfl.ch
000256573 909C0 $$xU12179$$pLIONS$$mvolkan.cevher@epfl.ch$$0252306
000256573 909CO $$pSTI$$pbook$$pchapter$$ooai:infoscience.epfl.ch:256573$$qGLOBAL_SET
000256573 960__ $$agosia.baltaian@epfl.ch
000256573 961__ $$afantin.reichler@epfl.ch
000256573 973__ $$aEPFL$$sSUBMITTED
000256573 980__ $$aBOOK_CHAP
000256573 981__ $$aoverwrite