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

Abstract

This paper offers a characterization of fundamental limits on the classification and reconstruction of high-dimensional signals from low-dimensional features, in the presence of side information. We consider a scenario where a decoder has access both to linear features of the signal of interest and to linear features of the side information signal; while the side information may be in a compressed form, the objective is recovery or classification of the primary signal, not the side information. The signal of interest and the side information are each assumed to have (distinct) latent discrete labels; conditioned on these two labels, the signal of interest and side information are drawn from a multivariate Gaussian distribution. With joint probabilities on the latent labels, the overall signal-(side information) representation is defined by a Gaussian mixture model. We then provide sharp sufficient and/or necessary conditions for these quantities to approach zero when the covariance matrices of the Gaussians are nearly low-rank. These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are a function of the number of linear features extracted from the signal of interest, the number of linear features extracted from the side information signal, and the geometry of these signals and their interplay. Moreover, on assuming that the signal of interest and the side information obey such an approximately low-rank model, we derive expansions of the reconstruction error as a function of the deviation from an exactly low-rank model; such expansions also allow identification of operational regimes where the impact of side information on signal reconstruction is most relevant. Our framework, which offers a principled mechanism to integrate side information in high-dimensional data problems, is also tested in the context of imaging applications.

62 pages, 11 figures, submitted to IEEE Transactions on Information Theory. The abstract of the paper is not reported entirely in the metadata due to length limitations

References in corpus (3)

• On asymptotic structure in compressed sensing
• Compressed Sensing with Prior Information: Optimal Strategies, Geometry, and Bounds
• Adaptive-Rate Sparse Signal Reconstruction With Application in Compressive Background Subtraction

Cited by in corpus (10)

• Compressive Hyperspectral Imaging with Side Information
• Multimodal Image Super-resolution via Joint Sparse Representations induced by Coupled Dictionaries
• Multi-modal dictionary learning for image separation with application in art investigation
• An Approximate Message Passing Framework for Side Information
• Heterogeneous Networked Data Recovery from Compressive Measurements Using a Copula Prior
• Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
• Multimodal Image Denoising based on Coupled Dictionary Learning
• Classification and Representation via Separable Subspaces: Performance Limits and Algorithms
• Statistical optimality conditions for compressive ensembles
• Multi-modal Image Processing based on Coupled Dictionary Learning