Publications

Recent first-author or joint-first-author publications/preprints, for a full overview see my Google Scholar page.

• Path-specific Objectives for Safer Agent Incentives
  Sebastian Farquhar, Ryan Carey, Tom Everitt
  AAAI 2022, BibTex

                    @article{farquhar_path-specific_2022,
                      title={Path-specific Objectives for Safer Agent Incentives},
                      author={Farquhar, Sebastian and Carey, Ryan and Everitt, Tom},
                      journal={Association for the Advancement of Artificial Intelligence},
                      year={2022}
                    }
                  

• Active Testing: Sample-Efficient Model Evaluation
  Jannik Kossen*, Sebastian Farquhar*, Yarin Gal, Tom Rainforth
  ICML 2021, BibTex

                    @article{kossen_active_2020,
                      title={Active Testing: Sample-Efficient Model Evaluation},
                      author={Kossen, Jannik and Farquhar, Sebastian and Gal, Yarin and Rainforth, Tom},
                      journal={International Conference on Machine Learning},
                      year={2021}
                    }
                  

  , Slides
• On Statistical Bias In Active Learning: How and When to Fix It
  Sebastian Farquhar*, Yarin Gal, Tom Rainforth*
  ICLR 2021 (Spotlight), BibTex

                    @article{farquhar_statistical_2020,
                      title={On Statistical Bias In Active Learning: How and When to Fix It},
                      author={Farquhar, Sebastian and Gal, Yarin and Rainforth, Tom},
                      journal={International Conference on Learning Representations},
                      year={2021}
                    }
                  

• Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
  Sebastian Farquhar, Lewis Smith, Yarin Gal
  NeurIPS 2020, BibTex

                    @article{farquhar_liberty_2020,
                      title={Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations},
                      author={Farquhar, Sebastian and Smith, Lewis and Gal, Yarin},
                      journal={Advances in Neural Information Processing Systems},
                      year={2020}
                    }
                  

  , Poster, Blog Post
• Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning
  Sebastian Farquhar, Michael Osborne, Yarin Gal
  AI Stats 2020, BibTex

                    @article{farquhar_radial_2020,
                      title={{Radial} {Bayesian} Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning},
                      author={Farquhar, Sebastian and Osborne, Michael and Gal, Yarin},
                      journal={Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics},
                      year={2020}
                    }
                  

  ,Code , Presentation Video, Blog Post
• Single Shot Structure Pruning Before Training
  Joost van Amersfoort*, Milad Alizadeh*, Sebastian Farquhar*, Nicholas Lane, Yarin Gal
  preprint, BibTex

                    @article{farquhar_single_2020,
                      title={Single Shot Structure Pruning Before Training},
                      author={van Amersfoort, Joost and Alizadeh, Milad and Farquhar, Sebastian and Lane, Nicholas and Gal, Yarin},
                      journal={preprint},
                      year={2020}
                    }
                  

• A Unifying Bayesian View of Continual Learning
  Sebastian Farquhar, Yarin Gal
  Bayesian Deep Learning Workshop at NeurIPS 2018 Spotlight Talk, BibTex

                    @article{farquhar_unifying_2018,
                      title = {A {Unifying} {Bayesian} {View} of {Continual} {Learning}},
                      language = {en},
                      journal = {Bayesian Deep Learning Workshop at NeurIPS},
                      author = {Farquhar, Sebastian and Gal, Yarin},
                      year = {2018}
                    }
                  

• Towards Robust Evaluations of Continual Learning
  Sebastian Farquhar, Yarin Gal
  Lifelong Learning: A Reinforcement Learning Approach at ICML 2018 Spotlight Talk, BibTex

                    @article{farquhar_towards_2018,
                      title = {Towards {Robust} {Evaluations} of {Continual} {Learning}},
                      journal = {Lifelong Learning: A Reinforcement Learning Approach Workshop at ICML},
                      author = {Farquhar, Sebastian and Gal, Yarin},
                      year = {2018}
                    }
                  

• Differentially Private Continual Learning
  Sebastian Farquhar, Yarin Gal
  Privacy in Machine Learning and AI Workshop at ICML 2018, BibTex

                    @article{farquhar_differentially_2018,
                        title = {Differentially {Private} {Continual} {Learning}},
                        language = {en},
                        journal = {Privacy in Machine Learning and AI workshop at ICML},
                        author = {Farquhar, Sebastian and Gal, Yarin},
                        year = {2018}
                    }
                  

• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
  Miles Brundage et al.
  arXiv, BibTex

                    @article{brundage2018malicious,
                      title={The malicious use of artificial intelligence: Forecasting, prevention, and mitigation},
                      author={Brundage, Miles and Avin, Shahar and Clark, Jack and Toner, Helen and Eckersley, Peter and Garfinkel, Ben and Dafoe, Allan and Scharre, Paul and Zeitzoff, Thomas and Filar, Bobby and others},
                      journal={arXiv preprint arXiv:1802.07228},
                      year={2018}
                    }
                  

• Pricing Externalities to Balance Public Risks and Benefits of Research
  Sebastian Farquhar, Owen Cotton-Barratt, Andrew Snyder-Beattie
  Health Security. Volume 15 Number 4. 2017 BibTex

                    @article{farquhar_pricing_2017,
                      title={Pricing Externalities to Balance Public Risks and Benefits of Research},
                      author={Farquhar, Sebastian and Cotton-Barratt, Owen and Snyder-Beattie, Andrew},
                      journal={Health Security},
                      volume={15},
                      number={4},
                      pages={401--408},
                      year={2017},
                      publisher={Mary Ann Liebert, Inc. 140 Huguenot Street, 3rd Floor New Rochelle, NY 10801 USA}
                    }
                  

Students

• Lorenz Kuhn (2021, co-supervised with Yarin Gal)
• Freddie Bickford Smith (2021, co-supervised with Tom Rainforth)

Reviewer

• Journal of Machine Learning Research (JMLR)
• International Journal of Computer Vision (IJCV)
• NeurIPS - 2019†, 2020, 2021†
• ICML - 2019, 2020†, 2021†
• ICLR - 2021, 2022
• AAAI - 2019

† Top reviewer certificate.

Community

• Co-organizer of Bayesian Deep Learning Workshop 2020, 2021 at NeurIPS
• Co-organizer of NeurIPS Approximate Inference in Bayesian Deep Learning Workshop 2021

Professional experience

Before my DPhil, I led the Global Priorities Project – a joint project of the Centre for Effective Altruism and the Future of Humanity Institute at the University of Oxford – which connects research from the University with the realities that policy-makers face in order to offer evidence-based non-partisan policy proposals. GPP focused on technological risk management and frameworks that encourage evidence-based policy-making.

I was Acting Executive Director of the Centre for Effective Altruism in 2015 – which works in Oxford to use evidence and analysis to make the world a better place, and runs Giving What We Can, 80,000 Hours and the Global Priorities Project in addition to building a community of effective altruists.

At McKinsey, I developed strategy for leading European public sector providers of services in health and social care, and helped to implement large-scale change programmes in local areas serving more than 2 million people.

Before McKinsey, I was on the team that set up 80,000 Hours – a social enterprise which helps people have a meaningful ethical career which now reaches over 1 million people a year, raised over $5 million in funding, and been featured by the Washington Post, the BBC, TED, and NPR among others.