Emilien Dupont

Emilien Dupont

Deep Learning, Generative Models

Hello! I’m a PhD student supervised by Yee Whye Teh and Arnaud Doucet, and a Deepmind Scholar. My research interests are mainly in representation learning and generative models, but I am interested in machine learning in general.

Before starting my PhD, I worked as a machine learning scientist in Silicon Valley for two years. I studied computational maths at Stanford University and theoretical physics at Imperial College.

Outside of machine learning, I also enjoy making visualizations of algorithms and concepts in maths.

Publications

2019

  • E. Dupont , A. Doucet , Y. W. Teh , Augmented Neural ODEs, in Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d’ Alché-Buc, E. Fox, and R. Garnett, Eds. Curran Associates, Inc., 2019, 3134–3144.

2018

  • E. Dupont , S. Suresha , Probabilistic Semantic Inpainting with Pixel Constrained CNNs, arXiv preprint arXiv:1810.03728, 2018.
  • E. Dupont , Learning Disentangled Joint Continuous and Discrete Representations, in Advances in Neural Information Processing Systems, 2018.
  • E. Dupont , T. Zhang , P. Tilke , L. Liang , W. Bailey , Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks, ICML TADGM Workshop, 2018.