Computing Upper and Lower Bounds on Likelihoods in Intractable Networks

02/13/2013
by   Tommi S. Jaakkola, et al.
0

We present deterministic techniques for computing upper and lower bounds on marginal probabilities in sigmoid and noisy-OR networks. These techniques become useful when the size of the network (or clique size) precludes exact computations. We illustrate the tightness of the bounds by numerical experiments.

READ FULL TEXT
research
05/19/2022

Exact lower and upper bounds for shifts of Gaussian measures

Exact upper and lower bounds on the ratio 𝖤w(𝐗-𝐯)/𝖤w(𝐗) for a centered G...
research
01/30/2013

Large Deviation Methods for Approximate Probabilistic Inference

We study two-layer belief networks of binary random variables in which t...
research
10/31/2017

The Stretch Factor of Hexagon-Delaunay Triangulations

The problem of computing the exact stretch factor (i.e., the tight bound...
research
06/24/2011

Bound Propagation

In this article we present an algorithm to compute bounds on the margina...
research
06/28/2020

Lookahead-Bounded Q-Learning

We introduce the lookahead-bounded Q-learning (LBQL) algorithm, a new, p...
research
06/16/2020

Debona: Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofs

Neural networks are commonly used in safety-critical real-world applicat...
research
09/04/2022

Computing geometric feature sizes for algebraic manifolds

We introduce numerical algebraic geometry methods for computing lower bo...

Please sign up or login with your details

Forgot password? Click here to reset