Statistical and Computational Efficiency for Smooth Tensor Estimation with Unknown Permutations

TL;DR

This paper introduces a new framework for smooth tensor denoising with unknown permutations, revealing phase transitions in smoothness requirements and proposing an efficient algorithm with proven optimality.

Contribution

It develops a general family of smooth tensor models, establishes minimax error bounds, and introduces a polynomial-time Borda count algorithm for optimal recovery.

Findings

A phase transition in smoothness threshold for optimal recovery.

A polynomial of degree up to (m-2)(m+1)/2 suffices for accurate tensor estimation.

The Borda count algorithm achieves the optimal rate under monotonicity.

Abstract

We consider the problem of structured tensor denoising in the presence of unknown permutations. Such data problems arise commonly in recommendation system, neuroimaging, community detection, and multiway comparison applications. Here, 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 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.