Dr

Atılım Güneş Baydin

Postdoctoral Researcher

TEL: 01865 273148
  • Biography
  • Research
  • Publications

Biography

Dr Atılım Güneş Baydin is a postdoctoral researcher in the Torr Vision Group, working at the intersection of generative modeling, probabilistic programming, and deep learning.

His current work is on enabling efficient probabilistic inference in large-scale simulators in particle physics, focusing on distributed training and inference at supercomputing scale. He collaborates with researchers at CERN, NASA, ESA, and other institutions on applications of machine learning to fundamental sciences.

Atlim is also a Research Member of the Common Room at Kellogg College and a research consultant to Microsoft Research Cambridge. He received his PhD in artificial intelligence from Universitat Autonoma de Barcelona in 2013. His research interests also include automatic differentiation, hyperparameter optimization, and evolutionary algorithms.

Personal website

Research Interests

  • Machine Learning
  • Deep Learning
  • Probabilistic Programming
  • Simulators

Research Groups

Related Academics

Working papers

Journal Publications

Refereed Conference Proceedings

Workshop Publications

  • Gram-Hansen, Bradley, Christian Schroeder, Philip H.S. Torr, Yee Whye Teh, Tom Rainforth, and Atılım Güneş Baydin. 2019. “Hijacking Malaria Simulators with Probabilistic Programming.” In ICML Workshop on AI for Social Good, Thirty-Sixth International Conference on Machine Learning (ICML 2019), Long Beach, CA, US.
  • Behl, Harkirat, Atılım Güneş Baydin, and Philip H.S. Torr. 2019. “Alpha MAML: Adaptive Model-Agnostic Meta-Learning.” In 6th ICML Workshop on Automated Machine Learning, Thirty-Sixth International Conference on Machine Learning (ICML 2019), Long Beach, CA, US.
  • Soboczenski, Frank, Michael D. Himes, Molly D. O’Beirne, Simone Zorzan, Atılım Güneş Baydin, Adam D. Cobb, Yarin Gal, Daniel Angerhausen, Massimo Mascaro, Giada N. Arney, and Shawn D. Domagal-Goldman. 2018. “Bayesian Deep Learning for Exoplanet Atmospheric Retrieval.” In Third Workshop on Bayesian Deep Learning (NeurIPS 2018), Montreal, Canada.
  • Milutinovic, Mitar, Atılım Güneş Baydin, Robert Zinkov, William Harvey, Dawn Song, Frank Wood, and Wade Shen. 2017. “End-to-End Training of Differentiable Pipelines Across Machine Learning Frameworks.” In Neural Information Processing Systems (NIPS) 2017 Autodiff Workshop: The Future of Gradient-Based Machine Learning Software and Techniques, Long Beach, CA, US, December 9, 2017.
  • Lezcano Casado, Mario, Atılım Güneş Baydin, David Martinez Rubio, Tuan Anh Le, Frank Wood, Lukas Heinrich, Gilles Louppe, Kyle Cranmer, Wahid Bhimji, Karen Ng, and Prabhat. 2017. “Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators.” In Neural Information Processing Systems (NIPS) 2017 Workshop on Deep Learning for Physical Sciences (DLPS), Long Beach, CA, US, December 8, 2017.
  • Le, Tuan Anh, Atılım Güneş Baydin, and Frank Wood. 2016. “Nested Compiled Inference for Hierarchical Reinforcement Learning.” In Neural Information Processing Systems (NIPS) 2016 Workshop on Bayesian Deep Learning, Barcelona, Spain, December 10, 2016.
  • Baydin, Atılım Güneş, and Barak A. Pearlmutter. 2015. “DiffSharp: Automatic Differentiation Library.” In International Conference on Machine Learning (ICML) Workshop on Machine Learning Open Source Software 2015: Open Ecosystems, Lille, France, July 10, 2015.
  • Baydin, Atılım Güneş, and Barak A. Pearlmutter. 2014. “Automatic Differentiation of Algorithms for Machine Learning.” In AutoML Workshop, International Conference on Machine Learning (ICML), Beijing, China, June 21–26, 2014.

Technical Reports

  • Himes, Michael D., Molly D. O’Beirne, Frank Soboczenski, Simone Zorzan, Atılım Güneş Baydin, Adam Cobb, Daniel Angerhausen, Giada N. Arney, and Shawn D. Domagal-Goldman. 2018. NASA Frontier Development Lab, Astrobiology Team II: From Biohints to Confirmed Evidence of Life: Possible Metabolisms Within Extraterrestrial Environmental Substrates. NASA Technical Memorandum.

Theses

Others/Unpublished