Approximate algorithms for neural-Bayesian approaches

AbstractWe describe two specific examples of neural-Bayesian approaches for complex modeling tasks: survival analysis and multitask learning. In both cases, we can come up with reasonable priors on the parameters of the neural network. As a result, the Bayesian approaches improve their (maximum likelihood) frequentist counterparts dramatically. By illustrating their application on the models under study, we review and compare algorithms that can be used for Bayesian inference: Laplace approximation, variational algorithms, Monte Carlo sampling, and empirical Bayes