Xiaoming Yuan (The University of Hong Kong): Implementing the ADMM to Big Datasets: A Case Study of LASSO

In this talk, I will focus on the application of the well known alternating direction method of multipliers (ADMM) to the LASSO model, and explain the mathematical issues arising from the big-data case where the dimensionality of variables is very high. Some implementation details will be analyzed and some numerical results for real datasets will be presented.