Anatoly Iambartsev (Institute of Mathematics and Statistics of the University of São Paulo, Brazil)
Title: Local Inverse Method: Constructing Networks with Local Partial Correlation
We revisit the Local Inverse Method for reconstructing complex networks from observational data, with a particular focus on scenarios where the number of variables exceeds the number of observations. This approach relies on estimating partial correlation coefficients, integrating both classical and Bayesian frameworks for structural inference. We provide an overview of previous results and discuss its applicability in new contexts, highlighting computational difficulties in recovering causal structures.