I am a fifth year PhD candidate in the UCI department of Statistics supervised by Professor Pierre Baldi and Daniel Gillen. My research focusses on hyperparameter search for machine learning models. Most recently my work has revolved around adjustment for uncertainty in the model training process during hyperparameter optimization. I am also actively developing Sherpa, a hyperparameter search Python library (see more below). In collaboration with Jianming Bian and the NOvA experiment at Fermilab, I am applying this work in the field of Neutrino Physics. I received my Bachelor of Science in Physics from Queen Mary, University of London and a Master of Science in Statistics from Imperial College London. I have done internships with Honda Research Institute, Apple, and Obsidian Security. Resume.


Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
Sherpa: Hyperparameter Optimization for Machine Learning Models
Convolutional Networks for Neutrino Energy Reconstruction
Approximate Inference for Deep Latent Gaussian Mixtures


Sherpa is an open-source hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks and can be used by anyone for free. With Sherpa, scientists can quickly optimize hyperparameters using a variety of powerful and interchangeable algorithms. Sherpa can be found here.