2018/06/10 by De Wen Soh, Soh, De Wen, Sekhar Tatikonda +1
Computer Science · #Bayesian Methods and Mixture Models #Bayesian Modeling and Causal Inference #Data Management and Algorithms #FOS: Mathematics #Statistics Theory (math.ST)
paper · pdf · doi:10.48550/arxiv.1806.03665
openalex publication_date 2018/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In high-dimensional graph learning problems, some topological properties of the graph, such as bounded node degree or tree structure, are typically assumed to hold so that the sample complexity of recovering the graph structure can be reduced. With bounded degree or separability assumptions, quantified by a measure k, a p-dimensional Gaussian graphical model (GGM) can be learnt with sample complexity Ω(k log p). Our work in this paper aims to do away with these assumptions by introducing an algorithm that can identify whether a GGM indeed has these topological properties without any initial topological assumptions. We show that we can check whether a GGM has node degree bounded by k with sample complexity Ω(k log p). More generally, we introduce the notion of a strongly K-separable GGM, and show that our algorithm can decide whether a GGM is strongly k-separable or not, with sample complexity Ω(k log p). We introduce the notion of a generalized feedback vertex set (FVS), an extension of the typical FVS, and show that we can use this identification technique to learn GGMs with generalized FVSs.