
Exploiting Evidence in Probabilistic Inference
We define the notion of compiling a Bayesian network with evidence and p...
read it

Using Qualitative Relationships for Bounding Probability Distributions
We exploit qualitative probabilistic relationships among variables for c...
read it

Towards a Mathematical Theory of Abstraction
While the utility of wellchosen abstractions for understanding and pred...
read it

ModelInvariant State Abstractions for ModelBased Reinforcement Learning
Accuracy and generalization of dynamics models is key to the success of ...
read it

Hierarchical Evidence Accumulation in the Pseiki System and Experiments in ModelDriven Mobile Robot Navigation
In this paper, we will review the process of evidence accumulation in th...
read it

Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxes
We present an approach for monitoring classification systems via data ab...
read it

Learning Baseline Values for Shapley Values
This paper aims to formulate the problem of estimating the optimal basel...
read it
Likelihood Computations Using Value Abstractions
In this paper, we use evidencespecific value abstraction for speeding Bayesian networks inference. This is done by grouping variable values and treating the combined values as a single entity. As we show, such abstractions can exploit regularities in conditional probability distributions and also the specific values of observed variables. To formally justify value abstraction, we define the notion of safe value abstraction and devise inference algorithms that use it to reduce the cost of inference. Our procedure is particularly useful for learning complex networks with many hidden variables. In such cases, repeated likelihood computations are required for EM or other parameter optimization techniques. Since these computations are repeated with respect to the same evidence set, our methods can provide significant speedup to the learning procedure. We demonstrate the algorithm on genetic linkage problems where the use of value abstraction sometimes differentiates between a feasible and nonfeasible solution.
READ FULL TEXT
Comments
There are no comments yet.