Mismatch in the Classification of Linear Subspaces: Sufficient Conditions for Reliable Classification

by   Jure Sokolic, et al.

This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix. We also assume that the classifier knows only a mismatched version of the parameters of input distribution in lieu of the true parameters. By constructing an asymptotic low-noise expansion of an upper bound to the error probability of such a mismatched classifier, we provide sufficient conditions for reliable classification in the low-noise regime that are able to sharply predict the absence of a classification error floor. Such conditions are a function of the geometry of the true signal distribution, the geometry of the mismatched signal distributions as well as the interplay between such geometries, namely, the principal angles and the overlap between the true and the mismatched signal subspaces. Numerical results demonstrate that our conditions for reliable classification can sharply predict the behavior of a mismatched classifier both with synthetic data and in a motion segmentation and a hand-written digit classification applications.


Bounds on the Number of Measurements for Reliable Compressive Classification

This paper studies the classification of high-dimensional Gaussian signa...

Classification and Reconstruction of High-Dimensional Signals from Low-Dimensional Features in the Presence of Side Information

This paper offers a characterization of fundamental limits on the classi...

Phase Retrieval for Signals in Union of Subspaces

We consider the phase retrieval problem for signals that belong to a uni...

Distributed detection of ARMA signals

This paper considers a distributed detection setup where agents in a net...

Retrieving Data Permutations from Noisy Observations: High and Low Noise Asymptotics

This paper considers the problem of recovering the permutation of an n-d...

An Upper Bound for the Distribution Overlap Index and Its Applications

This paper proposes an easy-to-compute upper bound for the overlap index...

Stochastic functional analysis with applications to robust machine learning

It is well-known that machine learning protocols typically under-utilize...

Please sign up or login with your details

Forgot password? Click here to reset