A0332
Title: Smooth tensor estimation with unknown permutations
Authors: Chanwoo Lee - University of Wisconsin - Madison (United States) [presenting]
Miaoyan Wang - University of Wisconsin - Madison (United States)
Abstract: The problem of structured tensor denoising in the presence of unknown permutations is considered. Such data problems arise commonly in recommendation systems, neuroimaging, community detection, and multiway comparison applications. We develop a general family of smooth tensor models up to arbitrary index permutations; the model incorporates the popular tensor block models and Lipschitz hypergraphon models as special cases. We show that a constrained least-squares estimator in the block-wise polynomial family achieves the minimax error bound. A phase transition phenomenon is revealed with respect to the smoothness threshold needed for optimal recovery. In particular, we find that a polynomial of degree up to $(m-2)(m+1)/2$ is sufficient for accurate recovery of order-m tensors, whereas a higher degree exhibits no further benefits. This phenomenon reveals the intrinsic distinction for smooth tensor estimation problems with and without unknown permutations. Furthermore, we provide an efficient polynomial-time Borda count algorithm that provably achieves optimal rate under monotonicity assumptions. The efficacy of our procedure is demonstrated through both simulations and Chicago crime data analysis.
