Stochastic Approximation for Online Tensorial Independent Component Analysis
This provides a theoretical foundation for online tensorial ICA, which is incremental as it builds on existing ICA methods with a focus on convergence analysis.
The paper tackles the problem of analyzing convergence for an online tensorial independent component analysis algorithm by framing it as a nonconvex stochastic approximation problem, achieving a sharp finite-sample error bound of $ ilde{O}(\sqrt{d/T})$ under mild assumptions and scaling conditions.
Independent component analysis (ICA) has been a popular dimension reduction tool in statistical machine learning and signal processing. In this paper, we present a convergence analysis for an online tensorial ICA algorithm, by viewing the problem as a nonconvex stochastic approximation problem. For estimating one component, we provide a dynamics-based analysis to prove that our online tensorial ICA algorithm with a specific choice of stepsize achieves a sharp finite-sample error bound. In particular, under a mild assumption on the data-generating distribution and a scaling condition such that $d^4/T$ is sufficiently small up to a polylogarithmic factor of data dimension $d$ and sample size $T$, a sharp finite-sample error bound of $\tilde{O}(\sqrt{d/T})$ can be obtained.