On Semi-supervised Estimation of Distributions
Name
erol-hsmerol-sm-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
646.8 KB
Format
Adobe PDF
Checksum (MD5)
84dd85879f47178edeaff66a83c3ae13
Author(s)
Erol, Hasan Sabri Melihcan
Advisor(s)
Zheng, Lizhong
Date Issued
June 2023
Publisher
Massachusetts Institute of Technology
Abstract
We study the problem of estimating the joint probability mass function (pmf) over two random variables. In particular, the estimation is based on the observation of 𝑚 samples containing both variables and 𝑛 samples missing one fixed variable. We adopt the minimax framework with [notation] loss functions, and we show that the composition of uni-variate minimax estimators achieves minimax risk with the optimal first-order constant for 𝑝 ≥ 2, in the regime 𝑚 = 𝑜(𝑛).
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
