1 code implementation • 17 Feb 2021 • Ashish Katiyar, Soumya Basu, Vatsal Shah, Constantine Caramanis
Furthermore, we present a polynomial time, sample efficient algorithm that recovers the exact tree when this is possible, or up to the unidentifiability as promised by our characterization, when full recoverability is impossible.
no code implementations • 10 Jun 2020 • Ashish Katiyar, Vatsal Shah, Constantine Caramanis
We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities.
no code implementations • 25 Jan 2019 • Ashish Katiyar, Jessica Hoffmann, Constantine Caramanis
If we observe realizations of the variables, we can compute the covariance matrix, and it is well known that the support of the inverse covariance matrix corresponds to the edges of the graphical model.