Learning Tensors From Partial Binary Measurements

DOI10.1109/TSP.2018.2879031zbMATH Open1414.15029arXiv1804.00108WikidataQ114083574 ScholiaQ114083574MaRDI QIDQ4628162FDOQ4628162

Authors: Navid Ghadermarzy, Özgür Yılmaz, Y. Plan 

Publication date: 6 March 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: In this paper we generalize the 1-bit matrix completion problem to higher order tensors. We prove that when $r=O(1)$ a bounded rank-$r$, order-$d$ tensor $T$ in $mathbb{R}^{N}imesmathbb{R}^{N}imescdotsimesmathbb{R}^N$ can be estimated efficiently by only $m=O(Nd)$ binary measurements by regularizing its max-qnorm and M-norm as surrogates for its rank. We prove that similar to the matrix case, i.e., when $d=2$, the sample complexity of recovering a low-rank tensor from 1-bit measurements of a subset of its entries is the same as recovering it from unquantized measurements. Moreover, we show the advantage of using 1-bit tensor completion over matricization both theoretically and numerically. Specifically, we show how the 1-bit measurement model can be used for context-aware recommender systems.

Full work available at URL: https://arxiv.org/abs/1804.00108

Recommendations

• Learning from binary multiway data: probabilistic tensor decomposition and its statistical optimality
• Learning with tensors: a framework based on convex optimization and spectral regularization
• Tensor decompositions for learning latent variable models
• Tensor decomposition for learning Gaussian mixtures from moments
• Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms
• Learning diagonal Gaussian mixture models and incomplete tensor decompositions
• Tensor Learning for Regression
• Learning a tensor subspace for semi-supervised dimensionality reduction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Multilinear algebra, tensor calculus (15A69) Matrix completion problems (15A83) Norms of matrices, numerical range, applications of functional analysis to matrix theory (15A60)

Cited In (6)

• One-bit tensor completion via transformed tensor singular value decomposition
• On computing high-dimensional Riemann theta functions
• Title not available (Why is that?)
• A Probit Tensor Factorization Model For Relational Learning
• Tensor completion based on triple tubal nuclear norm
• Minimax Lower Bounds on Dictionary Learning for Tensor Data

This page was built for publication: Learning Tensors From Partial Binary Measurements

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4628162)