“…Mathematically, the task can often be phrased as constructing valid confidence intervals/regions for both U and S based on the incomplete and corrupted observations {y l,j | (l, j) ∈ Ω}. Noteworthily, this model is frequently studied in econometrics and financial modeling under the name of factor models (Bai and Wang, 2016;Fan et al, 2021a;Fan and Yao, 2017;Gagliardini et al, 2019), and is closely related to the noisy matrix completion problem (except that the current goal is not to reconstruct all missing data) (Candès and Plan, 2010;Candès and Recht, 2009;Chi et al, 2019;Keshavan et al, 2010b).…”