Convergence rate of Bayesian tensor estimator: Optimal rate without restricted strong convexity
arXiv:1408.3092
Abstract
In this paper, we investigate the statistical convergence rate of a Bayesian low-rank tensor estimator. Our problem setting is the regression problem where a tensor structure underlying the data is estimated. This problem setting occurs in many practical applications, such as collaborative filtering, multi-task learning, and spatio-temporal data analysis. The convergence rate is analyzed in terms of both in-sample and out-of-sample predictive accuracies. It is shown that a near optimal rate is achieved without any strong convexity of the observation. Moreover, we show that the method has adaptivity to the unknown rank of the true tensor, that is, the near optimal rate depending on the true rank is achieved even if it is not known a priori.
arXiv comment27 pages, 2 figures
References in corpus (6)
- Simultaneous analysis of Lasso and Dantzig selector
- Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
- Estimation of high-dimensional low-rank matrices
- Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
- Bayesian methods for low-rank matrix estimation: short survey and theoretical study
- Bayesian factorizations of big sparse tensors