Bayesian computational technique

Multilevel Bayesian Neural Networks

Nov 1, 12:00 - 13:00

B9 L2 R2322

Bayesian computational technique Applied Machine Learning

Abstract In this talk we consider the application of multilevel Monte Carlo for Bayesian computation tasks in machine learning. There has recently been a synergy of statisticsand machine learning, promoting the application and development of new methodologies.Based on this we promote the use of multilevel Monte Carlo, which is a technique used toreduce the cost to attain a particular order of MSE with trace-class neural network priors. We provide some theoretical insights, and demonstrate the performance of our methodologyon different model problems such as classification and reinforcement