A Unit-Consistent Tensor Completion with Applications in Recommender Systems

04/04/2022
by   Tung Nguyen, et al.
1

In this paper we introduce a new consistency-based approach for defining and solving nonnegative/positive matrix and tensor completion problems. The novelty of the framework is that instead of artificially making the problem well-posed in the form of an application-arbitrary optimization problem, e.g., minimizing a bulk structural measure such as rank or norm, we show that a single property/constraint - preserving unit-scale consistency - guarantees both existence of a solution and, under relatively weak support assumptions, uniqueness. The framework and solution algorithms also generalize directly to tensors of arbitrary dimension while maintaining computational complexity that is linear in problem size for fixed dimension d. In the context of recommender system (RS) applications, we prove that two reasonable properties that should be expected to hold for any solution to the RS problem are sufficient to permit uniqueness guarantees to be established within our framework. This is remarkable because it obviates the need for heuristic-based statistical or AI methods despite what appear to be distinctly human/subjective variables at the heart of the problem. Key theoretical contributions include a general unit-consistent tensor-completion framework with proofs of its properties, including algorithms with optimal runtime complexity, e.g., O(1) term-completion with preprocessing complexity that is linear in the number of known terms of the matrix/tensor.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2022

A Simple and Scalable Tensor Completion Algorithm via Latent Invariant Constraint for Recommendation System

In this paper we provide a latent-variable formulation and solution to t...
research
07/17/2023

An Admissible Shift-Consistent Method for Recommender Systems

In this paper, we propose a new constraint, called shift-consistency, fo...
research
07/17/2023

Imposing Consistency Properties on Blackbox Systems with Applications to SVD-Based Recommender Systems

In this paper we discuss pre- and post-processing methods to induce desi...
research
03/31/2018

Learning tensors from partial binary measurements

In this paper we generalize the 1-bit matrix completion problem to highe...
research
12/02/2022

Some properties of the solution of the vertical tensor complementarity problem

In this paper, we mainly focus on the existence and uniqueness of the ve...
research
09/02/2020

Canonical Tensor Scaling

In this paper we generalize the canonical positive scaling of rows and c...
research
09/20/2021

Accelerated Stochastic Gradient for Nonnegative Tensor Completion and Parallel Implementation

We consider the problem of nonnegative tensor completion. We adopt the a...

Please sign up or login with your details

Forgot password? Click here to reset