Generalized Nonnegative Structured Kruskal Tensor Regression
By: Xinjue Wang , Esa Ollila , Sergiy A. Vorobyov and more
Potential Business Impact:
Finds hidden patterns in complex data.
This paper introduces Generalized Nonnegative Structured Kruskal Tensor Regression (NS-KTR), a novel tensor regression framework that enhances interpretability and performance through mode-specific hybrid regularization and nonnegativity constraints. Our approach accommodates both linear and logistic regression formulations for diverse response variables while addressing the structural heterogeneity inherent in multidimensional tensor data. We integrate fused LASSO, total variation, and ridge regularizers, each tailored to specific tensor modes, and develop an efficient alternating direction method of multipliers (ADMM) based algorithm for parameter estimation. Comprehensive experiments on synthetic signals and real hyperspectral datasets demonstrate that NS-KTR consistently outperforms conventional tensor regression methods. The framework's ability to preserve distinct structural characteristics across tensor dimensions while ensuring physical interpretability makes it especially suitable for applications in signal processing and hyperspectral image analysis.
Similar Papers
Tensor-on-tensor Regression Neural Networks for Process Modeling with High-dimensional Data
Machine Learning (CS)
Teaches computers to understand complex 3D shapes.
Functional Tensor Regression
Methodology
Helps understand brain scans with complex math.
Regularized Parameter Estimation in Mixed Model Trace Regression
Methodology
Finds patterns in complex data, like images.