PAC-learning bounded tree-width Graphical Models

07/11/2012
by   Mukund Narasimhan, et al.
0

We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Ho gen ([7]) have shown that this class is PAC-learnable by reducing it to a combinatorial optimization problem. However, for k > 1, this problem is NP-complete ([15]), and so unless P=NP, these approaches will take exponential amounts of time. Our approach differs significantly from these, in that it first attempts to find approximate conditional independencies by solving (polynomially many) submodular optimization problems, and then using a dynamic programming formulation to combine the approximate conditional independence information to derive a graphical model with underlying graph of the tree-width specified. This gives us an efficient (polynomial time in the number of random variables) PAC-learning algorithm which requires only polynomial number of samples of the true distribution, and only polynomial running time.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/25/2012

Learning Loosely Connected Markov Random Fields

We consider the structure learning problem for graphical models that we ...
research
01/24/2020

Discrete graphical models – an optimization perspective

This monograph is about discrete energy minimization for discrete graphi...
research
06/27/2012

Anytime Marginal MAP Inference

This paper presents a new anytime algorithm for the marginal MAP problem...
research
12/11/2012

Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs

We consider the problem of learning the structure of undirected graphica...
research
04/01/2020

A polynomial time algorithm to compute the connected tree-width of a series-parallel graph

It is well known that the treewidth of a graph G corresponds to the node...
research
09/12/2014

Hardness of parameter estimation in graphical models

We consider the problem of learning the canonical parameters specifying ...
research
06/14/2019

A New Family of Tractable Ising Models

We present a new family of zero-field Ising models over N binary variabl...

Please sign up or login with your details

Forgot password? Click here to reset