A1109
Title: Matrix completion with model-free weighting
Authors: Jiayi Wang - The University of Texas at Dallas (United States) [presenting]
Raymond Ka Wai Wong - Texas AM University (United States)
Xiaojun Mao - Shanghai Jiao Tong University (China)
Kwun Chuen Gary Chan - University of Washington (United States)
Abstract: A novel method is proposed for matrix completion under general non-uniform missing structures. By controlling an upper bound of a novel balancing error, we construct weights that can actively adjust for the non-uniformity in the empirical risk without explicitly modeling the observation probabilities, and can be computed efficiently via convex optimization. The recovered matrix based on the proposed weighted empirical risk enjoys appealing theoretical guarantees. In particular, the proposed method achieves a stronger guarantee than existing work in terms of scaling with respect to the observation probabilities under asymptotically heterogeneous missing settings (where entry-wise observation probabilities can be of different orders). These settings can be regarded as a better theoretical model of missing patterns with highly varying probabilities. We also provide a new minimax lower bound under a class of heterogeneous settings. Numerical experiments are also provided to demonstrate the effectiveness of the proposed method.
