Conor Durkan

I am a PhD student in machine learning at the University of Edinburgh, supervised by Iain Murray. I am broadly interested in deep generative modeling. My past work has focused on improving neural density estimators, and applying these models to likelihood-free inference problems.

Before coming to Edinburgh, I completed my undergrad in mathematical sciences at University College Cork, spending a year abroad at UC Berkeley.

In June 2020 I will be interning with Sander Dieleman at DeepMind in London.

Research

Conferences

Neural Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios
Advances in Neural Information Processing Systems, 2019
[arXiv] [GitHub]

Autoregressive Energy Machines
Charlie Nash, Conor Durkan
International Conference on Machine Learning, 2019
[arXiv] [GitHub]

Pre-prints

On Contrastive Learning for Likelihood-free Inference
Conor Durkan, Iain Murray, George Papamakarios
Pre-print, 2020
[arXiv] [GitHub]

Workshops

Cubic-Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios
First workshop on Invertible Neural Networks and Normalizing Flows (ICML), 2019
[arXiv]

Sequential Neural Methods for Likelihood-free Inference
Conor Durkan, George Papamakarios, Iain Murray
Third workshop on Bayesian Deep Learning (NeurIPS), 2018
[arXiv]

conormdurkan
conormdurkan

Contact

Email: conor.durkan@ed.ac.uk
Office: Room 2.51, Informatics Forum, 10 Crichton Street, Edinburgh, EH89AB