Convex recovery of tensors using nuclear norm penalization
This work addresses tensor recovery for applications in signal processing, statistics, and engineering, representing an incremental extension of matrix methods.
The paper tackles the problem of low-rank tensor recovery from linear random measurements by extending Tropp's matrix results to tensors, achieving recovery guarantees through nuclear norm penalization.
The subdifferential of convex functions of the singular spectrum of real matrices has been widely studied in matrix analysis, optimization and automatic control theory. Convex analysis and optimization over spaces of tensors is now gaining much interest due to its potential applications to signal processing, statistics and engineering. The goal of this paper is to present an applications to the problem of low rank tensor recovery based on linear random measurement by extending the results of Tropp to the tensors setting.