A0333
Title: Inference for low-rank models without rank estimation
Authors: Hyukjun Kwon - Rutgers University (United States) [presenting]
Yuan Liao - Rutgers University (United States)
Jungjun Choi - Rutgers University (United States)
Abstract: A new debiasing procedure is introduced for linear low-rank models, where the parameter of interest is a high-dimensional matrix coefficient. Our procedure achieves asymptotic normality without requiring knowledge of the true rank of the parameter matrix. The key feature of our approach is the use of diversified weights. We project an intermediate estimator onto low-rank linear spaces that are estimated using these weights. Notably, this projection is robust to the rank misspecification. However, the estimated projection matrices are inconsistent with the true projections, creating new challenges in characterizing the asymptotic distribution of our debiased estimator. Nonetheless, our proposed debiasing procedure successfully addresses these issues. Lastly, our procedure does not require sample splitting.
