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 learning.
Brief Biography
Since 2020 Dr. Neil Chada has been a research fellow under the supervision of Prof. Ajay Jasra, in the computational probability group. Prior to this he was a research fellow in statistics at the National University of Singapore between 2018 and 2020. He completed his PhD at the University of Warwick in 2018, with his topic focusing on both applied mathematics and statistics.