000002593 001__ 2593
000002593 005__ 20250829130907.0
000002593 0247_ $$2doi$$a10.6082/uchicago.2593
000002593 041__ $$aeng
000002593 245__ $$aAlgorithmic and Statistical Optimality for High-Dimensional Data
000002593 260__ $$bUniversity of Chicago
000002593 269__ $$a2020-08
000002593 300__ $$a89
000002593 336__ $$aDissertation
000002593 502__ $$bPh.D.
000002593 520__ $$aFor high-dimensional data, two of the most important questions are the question of algorithmic optimality, which asks for the optimal algorithm within a certain class of computationally feasible procedures, and the question of statistical optimality, which asks for the optimal statistical procedure under a generating model. In this thesis the question of algorithmic optimality is investigated for the class of iterative thresholding algorithms on sparse and low rank structures under the framework of restricted optimality. The question of statistical optimality is investigated for the high-dimensional sparse changepoint detection problem and the contaminated density estimation problem under the minimax framework.
000002593 542__ $$fUniversity of Chicago dissertations are covered by copyright.
000002593 650__ $$aStatistics
000002593 653__ $$aminimax
000002593 653__ $$anonconvex
000002593 653__ $$aoptimal
000002593 690__ $$aPhysical Sciences Division
000002593 691__ $$aStatistics
000002593 7001_ $$aLiu, Haoyang$$uUniversity of Chicago
000002593 72012 $$aRina F. Barber
000002593 72012 $$aChao Gao
000002593 72014 $$aMihai Anitescu
000002593 8564_ $$9d65e21b1-ab4d-4b86-89e4-848604f66a53$$ePublic$$s526277$$uhttps://knowledge.uchicago.edu/record/2593/files/Liu_uchicago_0330D_15373.pdf
000002593 909CO $$ooai:uchicago.tind.io:2593$$pDissertations$$pGLOBAL_SET
000002593 983__ $$aDissertation