Artur Bekasov

Photo of Artur I am a Machine Learning PhD student at the School of Informatics, University of Edinburgh, supervised by Iain Murray. I work on probabilistic machine learning, recently focusing on normalizing flows and uncertainty in deep learning. I am especially interested in the interplay between deep learning and Bayesian inference.

In addition, I’ve recently started with Amazon (Berlin) as a Machine Learning Scientist, coming back after interning with the team during the summer of 2020. Before joining Amazon full-time, I’ve undertook a machine learning research internship with Google Research (Zurich), where I’ve worked on modelling human motion with normalizing flows.

For my MSc thesis I have worked on generative video modelling via latent space transitions. Before that I worked on recommendations at Amazon (Edinburgh) and studied Computer Science at the University of Manchester, where my final-year project was on evolutionary computation.

Papers

Ordering Dimensions with Nested Dropout Normalizing Flows
Artur Bekasov, Iain Murray
Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, ICML, 2020
Selected for a spotlight
[arXiv] [code] [virtual poster talk]

Neural Spline Flows
Conor Durkan*, Artur Bekasov*, Iain Murray, George Papamakarios
NeurIPS, 2019
* Equal contribution
[NeurIPS] [arXiv] [code]

Cubic-Spline Flows
Conor Durkan*, Artur Bekasov*, Iain Murray, George Papamakarios
Workshop on Invertible Neural Nets and Normalizing Flows, ICML, 2019
* Equal contribution. Selected for a contributed talk
[arXiv] [code]

Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting
Artur Bekasov, Iain Murray
Bayesian Deep Learning Workshop, NeurIPS, 2018
Selected for a spotlight
[arXiv] [poster]

Also see my Google Scholar page.

Code

  • nflows: a modular PyTorch framework for building normalizing flow models.

Also see my GitHub page.

Teaching

I have tutored and marked for the following courses:

Community service

I’ve reviewed for:

  • NeurIPS (2021)
  • ICLR (2021)
  • Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, ICML (2020, 2021)

Contact