The Role of Principal Angles in Subspace Classification

Abstract

Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification. When the mismatch between the signal and the model is vanishingly small, the probability of misclassification is determined by the product of the sines of the principal angles between subspaces. When the mismatch is more significant, the probability of misclassification is determined by the sum of the squares of the sines of the principal angles. Reliability of classification is derived in terms of the distribution of signal energy across principal vectors. Larger principal angles lead to smaller classification error, motivating a linear transform that optimizes principal angles. The transform presented here (TRAIT) preserves some specific characteristic of each individual class, and this approach is shown to be complementary to a previously developed transform (LRT) that enlarges inter-class distance while suppressing intra-class dispersion. Theoretical results are supported by demonstration of superior classification accuracy on synthetic and measured data even in the presence of significant model mismatch.

References in corpus (3)

• Learning Transformations for Clustering and Classification
• Reconstruction of Signals Drawn from a Gaussian Mixture from Noisy Compressive Measurements
• Compressive Classification of a Mixture of Gaussians: Analysis, Designs and Geometrical Interpretation

Cited by in corpus (5)

• On the Adversarial Robustness of Subspace Learning
• Singular vector and singular subspace distribution for the matrix denoising model
• Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement
• Classification and Representation via Separable Subspaces: Performance Limits and Algorithms
• Learning optimally separated class-specific subspace representations using convolutional autoencoder