Distributionally robust structure learning for discrete pairwise markov networks

Y Li, Z Shi, X Zhang, B Ziebart - International Conference on …, 2022 - proceedings.mlr.press
We consider the problem of learning the underlying structure of a general discrete pairwise
Markov network. Existing approaches that rely on empirical risk minimization may perform …

Optimal rates for learning hidden tree structures

KE Nikolakakis, DS Kalogerias, AD Sarwate - arxiv preprint arxiv …, 2019 - arxiv.org
We provide high probability finite sample complexity guarantees for hidden non-parametric
structure learning of tree-shaped graphical models, whose hidden and observable nodes …