Sebastian Farquhar

According to our database, Sebastian Farquhar authored at least 31 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Evaluating Frontier Models for Dangerous Capabilities.

Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane

CoRR, 2024

Discovering Agents (Abstract Reprint).

Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Discovering agents.

Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt

Artif. Intell., September, 2023

Challenges with unsupervised LLM knowledge discovery.

Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah

CoRR, 2023

Model evaluation for extreme risks.

Toby Shevlane, Sebastian Farquhar, Ben Garfinkel, Mary Phuong, Jess Whittlestone, Jade Leung, Daniel Kokotajlo, Nahema Marchal, Markus Anderljung, Noam Kolt, Lewis Ho, Divya Siddarth, Shahar Avin, Will Hawkins, Been Kim, Iason Gabriel, Vijay Bolina, Jack Clark, Yoshua Bengio, Paul F. Christiano, Allan Dafoe

CoRR, 2023

Tracr: Compiled Transformers as a Laboratory for Interpretability.

David Lindner, János Kramár, Sebastian Farquhar, Matthew Rahtz, Tom McGrath, Vladimir Mikulik

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation.

Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Prediction-Oriented Bayesian Active Learning.

Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Do Bayesian Neural Networks Need To Be Fully Stochastic?

Mrinank Sharma, Sebastian Farquhar, Eric T. Nalisnick, Tom Rainforth

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

CLAM: Selective Clarification for Ambiguous Questions with Large Language Models.

Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

CoRR, 2022

Understanding Approximation for Bayesian Inference in Neural Networks.

Sebastian Farquhar

CoRR, 2022

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation.

Jannik Kossen, Sebastian Farquhar, Yarin Gal, Thomas Rainforth

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt.

Sören Mindermann, Jan Markus Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal

Proceedings of the International Conference on Machine Learning, 2022

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients.

Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal

Proceedings of the Tenth International Conference on Learning Representations, 2022

Path-Specific Objectives for Safer Agent Incentives.

Sebastian Farquhar, Ryan Carey, Tom Everitt

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Prioritized training on points that are learnable, worth learning, and not yet learned.

Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Markus Brauner, Yarin Gal

CoRR, 2021

A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions.

Andreas Kirsch, Sebastian Farquhar, Yarin Gal

CoRR, 2021

Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning.

Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Z. Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran

CoRR, 2021

Evaluating Approximate Inference in Bayesian Deep Learning.

Andrew Gordon Wilson, Pavel Izmailov, Matthew D. Hoffman, Yarin Gal, Yingzhen Li, Melanie F. Pradier, Sharad Vikram, Andrew Y. K. Foong, Sanae Lotfi, Sebastian Farquhar

Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Active Testing: Sample-Efficient Model Evaluation.

Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth

Proceedings of the 38th International Conference on Machine Learning, 2021

On Statistical Bias In Active Learning: How and When to Fix It.

Sebastian Farquhar, Yarin Gal, Tom Rainforth

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Single Shot Structured Pruning Before Training.

Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar, Nicholas D. Lane, Yarin Gal

CoRR, 2020

Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks.

Sebastian Farquhar, Lewis Smith, Yarin Gal

CoRR, 2020

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations.

Sebastian Farquhar, Lewis Smith, Yarin Gal

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning.

Sebastian Farquhar, Michael A. Osborne, Yarin Gal

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks.

Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G. J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon, Yarin Gal

CoRR, 2019

Radial Bayesian Neural Networks: Robust Variational Inference In Big Models.

Sebastian Farquhar, Michael A. Osborne, Yarin Gal

CoRR, 2019

Differentially Private Continual Learning.

Sebastian Farquhar, Yarin Gal

CoRR, 2019

A Unifying Bayesian View of Continual Learning.

Sebastian Farquhar, Yarin Gal

CoRR, 2019

2018

Towards Robust Evaluations of Continual Learning.

Sebastian Farquhar, Yarin Gal

CoRR, 2018

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.

Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum S. Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei

CoRR, 2018