
GP
Gianluigi Pillonetto, Mauro Bisiacco
· 1 min read
ResearcharXiv cs.LG
Stability-compatible kernels: beyond Gaussianity for impulse response estimation
arXiv:2611.24272v1 Announce Type: cross
Abstract: Kernel-based regularization for linear system identification uses positive semidefinite kernels both to define reproducing kernel Hilbert spaces (RKHSs) and as covariance models for stochastic impulse responses. Sharp kernel conditions are known for RKHS stability, while almost-sure BIBO stability under Gaussian priors requires an even more restrictive covariance condition. These restrictions, however, need not persist beyond Gaussianity, where the covariance no longer determines the full probability law. We introduce the notion of a stability-compatible kernel, namely a covariance kernel admitting at least one stochastic realization with almost-surely absolutely summable sample paths. We show that stability-compatibility holds if and only if the stable elements are dense in the associated RKHS, a condition strictly weaker than RKHS stability, and derive practical sufficient conditions, including a spectral criterion for stationary kernels. We then construct non-Gaussian priors that preserve a prescribed covariance while enforcing almost-sure stability. In particular, this yields a stable prior based on the stationary radial-basis-function (RBF) kernel, separating covariance structure from the mechanism enforcing stability. Numerical experiments show substantial estimation gains for several important classes of impulse responses, with particularly pronounced advantages when relevant dynamics occur at late lags or in separated temporal regions.
Original source
This story was published by arXiv cs.LG and written by Gianluigi Pillonetto, Mauro Bisiacco. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


