We are pleased to announce OMI Faculty, Students and Associates have had six full papers accepted at one of the top Machine Learning conferences, NeurIPS.


Jack Parker-Holder, Vu Nguyen and Stephen Roberts
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts
Effective Diversity in Population Based Reinforcement Learning (accepted for oral presentation)

Alexander Camuto, Matthew Willetts, Umut Şimşekli, Stephen Roberts, Chris Holmes
Explicit Regularisation in Gaussian Noise Injections

Vu Nguyen, Sebastian Schulze, Michael A. Osborne
Bayesian Optimization for Iterative Learning

Vu Nguyen, Vaden Masrani, Rob Brekelmans, Michael A. Osborne, Frank Wood
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

Jack Parker-Holder, Cinjon Resnick, Luke Metz, Hengyuan Hu, Adam Lerer, Alistair HP Letcher, Alex Peysakhovich, Aldo Pacchiano, Jakob Foerster
Ridge Riding: Finding diverse solutions by following eigenvectors of the Hessian

Xinshi Chen, Yufei Zhang, Christoph Reisinger, Le Song
Understanding Deep Architectures with Reasoning Layer