activity
20182022
most citedA Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks

73 citations · 156 across the 7 of their papers we have counts for

collaborators

11 papers

stat.ML2022

Understanding Approximation for Bayesian Inference in Neural Networks

Sebastian Farquhar

Bayesian inference has theoretical attractions as a principled framework for reasoning about beliefs. However, the motivations of Bayesian inference which claim it to be the only '…

cs.AI20223 cited

Path-Specific Objectives for Safer Agent Incentives

Sebastian Farquhar, Ryan Carey, Tom Everitt

We present a general framework for training safe agents whose naive incentives are unsafe. As an example, manipulative or deceptive behaviour can improve rewards but should be avoi…

cs.LG202211 cited

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

Milad Alizadeh, Shyam A. Tailor, Luisa M Zintgraf +4

Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for t…

stat.ML2021

Active Testing: Sample-Efficient Model Evaluation

Jannik Kossen, Sebastian Farquhar, Yarin Gal +1

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model t…

stat.ML2021

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

Sebastian Farquhar, Yarin Gal, Tom Rainforth

Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize…

cs.LG202015 cited

Single Shot Structured Pruning Before Training

Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar +2

We introduce a method to speed up training by 2x and inference by 3x in deep neural networks using structured pruning applied before training. Unlike previous works on pruning befo…