Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder

06/16/2021
by   Qi Lyu, et al.
0

This work focuses on the problem of unraveling nonlinearly mixed latent components in an unsupervised manner. The latent components are assumed to reside in the probability simplex, and are transformed by an unknown post-nonlinear mixing system. This problem finds various applications in signal and data analytics, e.g., nonlinear hyperspectral unmixing, image embedding, and nonlinear clustering. Linear mixture learning problems are already ill-posed, as identifiability of the target latent components is hard to establish in general. With unknown nonlinearity involved, the problem is even more challenging. Prior work offered a function equation-based formulation for provable latent component identification. However, the identifiability conditions are somewhat stringent and unrealistic. In addition, the identifiability analysis is based on the infinite sample (i.e., population) case, while the understanding for practical finite sample cases has been elusive. Moreover, the algorithm in the prior work trades model expressiveness with computational convenience, which often hinders the learning performance. Our contribution is threefold. First, new identifiability conditions are derived under largely relaxed assumptions. Second, comprehensive sample complexity results are presented – which are the first of the kind. Third, a constrained autoencoder-based algorithmic framework is proposed for implementation, which effectively circumvents the challenges in the existing algorithm. Synthetic and real experiments corroborate our theoretical analyses.

READ FULL TEXT
research
10/14/2022

Provable Subspace Identification Under Post-Nonlinear Mixtures

Unsupervised mixture learning (UML) aims at identifying linearly or nonl...
research
06/14/2022

On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis

Nonlinear independent component analysis (nICA) aims at recovering stati...
research
09/19/2019

Neural Network-Assisted Nonlinear Multiview Component Analysis: Identifiability and Algorithm

Multiview analysis aims at extracting shared latent components from data...
research
04/17/2021

Model-Based Deep Autoencoder Networks for Nonlinear Hyperspectral Unmixing

Autoencoder (AEC) networks have recently emerged as a promising approach...
research
01/06/2019

Learning Nonlinear Mixtures: Identifiability and Algorithm

Linear mixture models have proven very useful in a plethora of applicati...
research
04/14/2016

Unsupervised Nonlinear Spectral Unmixing based on a Multilinear Mixing Model

In the community of remote sensing, nonlinear mixing models have recentl...
research
08/26/2019

Convex Programming for Estimation in Nonlinear Recurrent Models

We propose a formulation for nonlinear recurrent models that includes si...

Please sign up or login with your details

Forgot password? Click here to reset