Large Dimensional Independent Component Analysis: Statistical Optimality and Computational Tractability

Stochastics Seminar
Thursday, November 17, 2022 - 3:30pm for 1 hour (actually 50 minutes)
Skiles 006
Ming Yuan – Columbia University
Cheng Mao

Independent component analysis is a useful and general data analysis tool. It has found great successes in many applications. But in recent years, it has been observed that many popular approaches to ICA do not scale well with the number of components. This debacle has inspired a growing number of new proposals. But it remains unclear what the exact role of the number of components is on the information theoretical limits and computational complexity for ICA. Here I will describe our recent work to specifically address these questions and introduce a refined method of moments that is both computationally tractable and statistically optimal.