【Winter 2021】Rank Regularized Estimation of Approximate Factor Models
In this report, we summarize the major findings by Bai and Ng (2019), and apply the rank-regularized approximate factor models to a real-world dataset. For the theoretical part, we first describe the problem notations and settings. Then we present two classical estimations of approximate factor models without regularization. Next we discuss the rank minimization in broader machine learning literature. Finally, we combine the arguments from the previous two parts and estimate the approximate factor model with the rank regularization.