Robust and highly scalable estimation of directional couplings from time-shifted signals
This addresses a central methodological challenge in fields like neuroscience and economics by offering a robust and scalable solution for network coupling estimation from delayed measurements.
The paper tackles the ill-posed problem of estimating directed couplings in networks from time-shifted signals by using a variational Bayes framework that marginalizes delay uncertainty to obtain conservative estimates. In ground-truth experiments, the method provides reliable coupling estimates, greatly outperforming similar approaches like regression DCM.
The estimation of directed couplings between the nodes of a network from indirect measurements is a central methodological challenge in scientific fields such as neuroscience, systems biology and economics. Unfortunately, the problem is generally ill-posed due to the possible presence of unknown delays in the measurements. In this paper, we offer a solution of this problem by using a variational Bayes framework, where the uncertainty over the delays is marginalized in order to obtain conservative coupling estimates. To overcome the well-known overconfidence of classical variational methods, we use a hybrid-VI scheme where the (possibly flat or multimodal) posterior over the measurement parameters is estimated using a forward KL loss while the (nearly convex) conditional posterior over the couplings is estimated using the highly scalable gradient-based VI. In our ground-truth experiments, we show that the network provides reliable and conservative estimates of the couplings, greatly outperforming similar methods such as regression DCM.