Sample, computation vs storage tradeoffs for classification using tensor subspace models

2017/06/18 by Mohammadhossein Chaghazardi, Chaghazardi, Mohammadhossein, Shuchin Aeron +1
Computer Science · Mathematics · Medicine · #Advanced Neuroimaging Techniques and Applications #Algorithms and Data Compression #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Tensor decomposition and applications

paper · pdf · doi:10.48550/arxiv.1706.05599

openalex publication_date 2017/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we exhibit the tradeoffs between the (training) sample, computation and storage complexity for the problem of supervised classification using signal subspace estimation. Our main tool is the use of tensor subspaces, i.e. subspaces with a Kronecker structure, for embedding the data into lower dimensions. Among the subspaces with a Kronecker structure, we show that using subspaces with a hierarchical structure for representing data leads to improved tradeoffs. One of the main reasons for the improvement is that embedding data into these hierarchical Kronecker structured subspaces prevents overfitting at higher latent dimensions.

Citations

• Tensor Decomposition for Signal Processing and Machine Learning

Related

• Common Mode Patterns for Supervised Tensor Subspace Learning
• Tensor Matched Kronecker-Structured Subspace Detection for Missing Information
• Stochastic tensor space feature theory with applications to robust machine learning
• Linear Tensor Projection Revealing Nonlinearity
• Structure from Local Optima: Learning Subspace Juntas via Higher Order PCA