Approximability of Probability Distributions

We consider the question of how well a given distribution can be approximated with probabilistic graphical models. We introduce a new parameter, effective treewidth, that captures the degree of approximability as a tradeoff between the accuracy and the complexity of approximation. We present a simple approach to analyzing achievable tradeoffs that exploits the threshold behavior of monotone graph properties, and provide experimental results that support the approach.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Alina Beygelzimer, Irina Rish
• Keywords: Achievable Tradeoffs, Monotone Graph Properties, NIPS 2003, NIPS 2007, Probabilistic Graphical Models