On a low-rank matrix single index model
arXiv:2210.08851 · doi:10.3390/math11092065
Abstract
In this paper, we present a theoretical study of a low-rank matrix single index model. This model is recently introduced in biostatistics however its theoretical properties on estimating together the link function and the coefficient matrix are not yet carried out. Here, we advance on using PAC-Bayesian bounds technique to provide a rigorous theoretical understanding for jointly estimation of the link function and the coefficient matrix.
References in corpus (5)
- Estimation of high-dimensional low-rank matrices
- Variable selection for general index models via sliced inverse regression
- Pseudo-Bayesian Quantum Tomography with Rank-adaptation
- Matrix Completion Under Monotonic Single Index Models
- Any Orthonormal Basis in High Dimension is Uniformly Distributed over the Sphere