R.D. Turner

About

R.D. Turner is a leading researcher in Bayesian optimization and Gaussian process (GP) methods, whose work bridges the gap between theoretical rigor and practical scalability. Turner’s primary contributions lie in developing robust, sample-efficient algorithms for optimizing expensive black-box functions and for state estimation in nonlinear dynamic systems. Their most influential work, "Scalable Global Optimization via Local Bayesian Optimization" (2019), with 144 citations, addresses a critical bottleneck in the field: applying Bayesian optimization to high-dimensional problems with thousands of observations. This paper introduced a novel local modeling approach that dramatically improves scalability without sacrificing performance, making Bayesian optimization viable for complex, real-world tasks. Earlier, Turner’s foundational paper "Robust Filtering and Smoothing with Gaussian Processes" (2012), with 82 citations, pioneered a principled framework for robust Bayesian filtering and smoothing when both transition and measurement functions are modeled as GPs. This work has been instrumental in advancing signal processing and robotics, where accurate state estimation under uncertainty is paramount. Turner’s research continues to shape how practitioners apply probabilistic models to challenging optimization and filtering problems, with their methods now widely adopted across machine learning and control.

Research Focus

Key Achievements

Top Papers

1. 1
   Scalable Global Optimization via Local Bayesian Optimization

   144 citations · 2019
2. 2
   1 Robust Filtering and Smoothing with Gaussian Processes

   82 citations · 2012

Key Collaborators

Contact & Links