Tensor denoising and completion based on ordinal observations
This work addresses tensor denoising and completion for applications like neuroimaging and recommendation systems, offering a novel method with strong theoretical guarantees.
The authors tackled the problem of low-rank tensor estimation from incomplete, ordinal-valued observations, proposing a multi-linear cumulative link model and a rank-constrained M-estimator that achieves minimax optimality with a faster convergence rate and consistent recovery using only O(Kd) noisy, quantized observations.
Higher-order tensors arise frequently in applications such as neuroimaging, recommendation system, social network analysis, and psychological studies. We consider the problem of low-rank tensor estimation from possibly incomplete, ordinal-valued observations. Two related problems are studied, one on tensor denoising and the other on tensor completion. We propose a multi-linear cumulative link model, develop a rank-constrained M-estimator, and obtain theoretical accuracy guarantees. Our mean squared error bound enjoys a faster convergence rate than previous results, and we show that the proposed estimator is minimax optimal under the class of low-rank models. Furthermore, the procedure developed serves as an efficient completion method which guarantees consistent recovery of an order-$K$ $(d,\ldots,d)$-dimensional low-rank tensor using only $\tilde{\mathcal{O}}(Kd)$ noisy, quantized observations. We demonstrate the outperformance of our approach over previous methods on the tasks of clustering and collaborative filtering.