Seminars Events Calendar

Filter by
Jump to

Non-Convex Optimization Through Stochastic Gradient Descent, Phase Retrieval As A Case Study

Prof Yan Shuo TanUniversity of California, Berkley

Date:24 July 2019, Wednesday

Location:S16-05-96, DSAP Computer Lab 4

Time:03:00PM to 04:00PM

Gini index is a widely used measure of economic inequality. Apart from measuring economic inequality, the Gini index is used to measure inequality in education, inequality of health related quality of life in a population and others. The problem is to construct a narrow confidence interval for Gini index with a specified confidence coefficient and a specified width without assuming any specific distribution of the data. Fixed sample size planning methods cannot give a sufficiently narrow width with high coverage probability. In this presentation, we propose a sequential procedure for constructing sufficiently narrow confidence intervals for Gini Index using smallest possible sample size, importantly without specific distributional assumptions. The characteristics of this sequential procedure will also be discussed in the presentation. An extension of this work and its application will be discussed briefly as well.