Computing upper and lower bounds on likelihoods in intractable networks
نویسندگان
چکیده
We present deterministic techniques for com puting upper and lower bounds on marginal probabilities in sigmoid and noisy-OR net works. These techniques become useful when the size of the network (or clique size) pre cludes exact computations. We illustrate the tightness of the bounds by numerical experi ments.
منابع مشابه
A Survey on Stability Measure of Networks
In this paper we discuss about tenacity and its properties in stability calculation. We indicate relationships between tenacity and connectivity, tenacity and binding number, tenacity and toughness. We also give good lower and upper bounds for tenacity.
متن کاملUpper and lower bounds of symmetric division deg index
Symmetric Division Deg index is one of the 148 discrete Adriatic indices that showed good predictive properties on the testing sets provided by International Academy of Mathematical Chemistry. Symmetric Division Deg index is defined by $$ SDD(G) = sumE left( frac{min{d_u,d_v}}{max{d_u,d_v}} + frac{max{d_u,d_v}}{min{d_u,d_v}} right), $$ where $d_i$ is the degree of vertex $i$ in graph $G$. In th...
متن کاملOn the total version of geometric-arithmetic index
The total version of geometric–arithmetic index of graphs is introduced based on the endvertex degrees of edges of their total graphs. In this paper, beside of computing the total GA index for some graphs, its some properties especially lower and upper bounds are obtained.
متن کاملOn Reversing Jensen's Inequality
Alex Pentland MIT Media Lab Cambridge, MA 02139 [email protected] Jensen's inequality is a powerful mathematical tool and one of the workhorses in statistical learning. Its applications therein include the EM algorithm, Bayesian estimation and Bayesian inference. Jensen computes simple lower bounds on otherwise intractable quantities such as products of sums and latent log-likelihoods. This s...
متن کاملA bi-level linear programming problem for computing the nadir point in MOLP
Computing the exact ideal and nadir criterion values is a very important subject in multi-objective linear programming (MOLP) problems. In fact, these values define the ideal and nadir points as lower and upper bounds on the nondominated points. Whereas determining the ideal point is an easy work, because it is equivalent to optimize a convex function (linear function) over a con...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1996