Gaussian Probabilities and Expectation Propagation
arXiv:1111.6832
Abstract
While Gaussian probability densities are omnipresent in applied mathematics, Gaussian cumulative probabilities are hard to calculate in any but the univariate case. We study the utility of Expectation Propagation (EP) as an approximate integration method for this problem. For rectangular integration regions, the approximation is highly accurate. We also extend the derivations to the more general case of polyhedral integration regions. However, we find that in this polyhedral case, EP's answer, though often accurate, can be almost arbitrarily wrong. We consider these unexpected results empirically and theoretically, both for the problem of Gaussian probabilities and for EP more generally. These results elucidate an interesting and non-obvious feature of EP not yet studied in detail.
References in corpus (3)
Cited by in corpus (15)
- Skew-t Filter and Smoother with Improved Covariance Matrix Approximation
- Expectation propagation as a way of life: A framework for Bayesian inference on partitioned data
- Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
- GLASSES: Relieving The Myopia Of Bayesian Optimisation
- Stochastic Expectation Propagation
- Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
- Expectation Propagation for Poisson Data
- Integrals over Gaussians under Linear Domain Constraints
- Sparse Probit Linear Mixed Model
- Batched Bayesian optimization by maximizing the probability of including the optimum
- A probabilistic framework for cosmological inference of peculiar velocities
- Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
- Entropy Search for Information-Efficient Global Optimization
- Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
- A Dynamic Programming Approach to Evaluating Multivariate Gaussian Probabilities