Timezone: »
We consider the problem of learning the underlying graph of an unknown Ising model on p spins from a collection of i.i.d. samples generated from the model. We suggest a new estimator that is computationally efficient and requires a number of samples that is near-optimal with respect to previously established information theoretic lower-bound. Our statistical estimator has a physical interpretation in terms of "interaction screening". The estimator is consistent and is efficiently implemented using convex optimization. We prove that with appropriate regularization, the estimator recovers the underlying graph using a number of samples that is logarithmic in the system size p and exponential in the maximum coupling-intensity and maximum node-degree.
Author Information
Marc Vuffray (Los Alamos National Laboratory)
I’m a staff research scientist in the Theoretical Division at the Los Alamos National Laboratory (LANL), New Mexico, where I am part of the Advanced Network Science Initiative (ANSI) as well as the Condensed Matter and Complex Systems Group (T-4). My background is in statistical physics and information theory. My current work focuses on the design of machine learning techniques for learning probabilistic networks and on the development of new methods to control and optimize energy networks under uncertainty.
Sidhant Misra (Los Alamos National Laboratory)
Andrey Lokhov (Los Alamos National Laboratory)
Michael Chertkov (Los Alamos National Laboratory)
More from the Same Authors
-
2022 : Energy based models for tomography of quantum spin-lattice systems »
Abhijith Jayakumar · Marc Vuffray · Andrey Lokhov -
2020 Poster: Efficient Learning of Discrete Graphical Models »
Marc Vuffray · Sidhant Misra · Andrey Lokhov -
2020 Poster: Learning of Discrete Graphical Models with Neural Networks »
Abhijith Jayakumar · Andrey Lokhov · Sidhant Misra · Marc Vuffray -
2017 Poster: Gauging Variational Inference »
Sungsoo Ahn · Michael Chertkov · Jinwoo Shin -
2016 Poster: Synthesis of MCMC and Belief Propagation »
Sungsoo Ahn · Michael Chertkov · Jinwoo Shin -
2016 Oral: Synthesis of MCMC and Belief Propagation »
Sungsoo Ahn · Michael Chertkov · Jinwoo Shin -
2016 Poster: Reconstructing Parameters of Spreading Models from Partial Observations »
Andrey Lokhov -
2015 Poster: Minimum Weight Perfect Matching via Blossom Belief Propagation »
Sungsoo Ahn · Sejun Park · Michael Chertkov · Jinwoo Shin -
2015 Spotlight: Minimum Weight Perfect Matching via Blossom Belief Propagation »
Sungsoo Ahn · Sejun Park · Michael Chertkov · Jinwoo Shin