Maximum Likelihood Bounded Tree-Width Markov Networks
Abstract:
We study the problem of projecting a distribution onto (or finding a maximum likelihood distribution among) Markov networks of bounded tree-width. By casting it as the combinatorial optimization problem of finding a maximum weight hypertree, we prove that it is NP-hard to solve exactly and provide an approximation algorithm with a provable performance guarantee. 1
Citations
| 1290 | The Probabilistic Method – Alon, Spencer, et al. - 1992 |
| 345 | Approximating discrete probability distributions with dependence trees – Chow, Liu - 1968 |
| 83 | Learning Bayesian networks is NP-complete, in: D – Chickering - 1996 |
| 24 | Learning Markov networks: Maximum bounded tree-width graphs – Karger, Srebro - 2001 |
| 20 | Approximating discrete probability distributions with decomposable models – Malvestuto - 1991 |
| 15 | Learning polytrees, in – Dasgupta - 1999 |
| 14 | Learning with mixtures of trees – Meila-Predoviciu - 1999 |
| 8 | Maximum likelihood Markov networks: An algorithmic approach – Srebro - 2000 |
