This paper introduces a novel moment problem for estimating the power spectral density of Vector-valued Autoregressive Moving-Average (VARMA) processes. Unlike existing methods that require a fixed or scalar moving-average component, this new approach utilizes transportation entropy to learn the spectral density without such restrictions. The proposed method expands the class of ARMA models for which optimal spectral densities can be sought. AI
IMPACT This research may lead to improved methods for analyzing time-series data, potentially impacting AI models that rely on such data for forecasting or pattern recognition.
RANK_REASON The cluster contains a single academic paper on a statistical method. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →