Reservoir Subspace Injection for Online ICA under Top-n Whitening
Not on the map. Why?
Abstract (arXiv)
Reservoir expansion can improve online independent component analysis (ICA) under nonlinear mixing, yet top-n whitening may discard injected features. We formalize this bottleneck as reservoir subspace injection (RSI): injected features help only if they enter the retained eigenspace without displacing passthrough directions. RSI diagnostics (IER, SSO, ρx) identify a failure mode in our top-n setting: stronger injection increases IER but crowds out passthrough energy (ρx: 1.00!rightarrow!0.77), degrading SI-SDR by up to 2.2,dB. A guarded RSI controller preserves passthrough retention and recovers mean performance to within 0.1,dB of baseline 1/N scaling. With passthrough preserved, RE-OICA improves over vanilla online ICA by +1.7,dB under nonlinear mixing and achieves positive SI-SDRsc on the tested super-Gaussian benchmark (+0.6,dB).
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 33 references that are in the map. First posted on arXiv 2 Mar 2026.
Builds on
9 of 33 references.
References · 9
- 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
- 2018SDR - half-baked or well done?cited by 420
- 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
- 2018Echo state networks are universalcited by 86
- 2023Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learningcited by 48
- 2020Reservoir Computing meets Recurrent Kernels and Structured Transformscited by 15
- 2013Independent Vector Analysis: Identification Conditions and Performance Boundscited by 7
- 2024Signal-noise separation using unsupervised reservoir computingcited by 3
- 2025Echo State Networks as State-Space Models: A Systems Perspectivecited by 2
Built on by
Not cited yet.