activity
20182025
most citedA Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks

73 citations · 320 across the 16 of their papers we have counts for

collaborators
Showing 2022Show all

8 papers · 1 filter

cs.CL2022★ 7 cited

CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models

Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

Users often ask dialogue systems ambiguous questions that require clarification. We show that current language models rarely ask users to clarify ambiguous questions and instead pr…

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.LG2022★ 7 cited

Do Bayesian Neural Networks Need To Be Fully Stochastic?

Mrinank Sharma, Sebastian Farquhar, Eric Nalisnick +1

We investigate the benefit of treating all the parameters in a Bayesian neural network stochastically and find compelling theoretical and empirical evidence that this standard cons…

cs.AI2022★ 7 cited

Discovering Agents

Zachary Kenton, Ramana Kumar, Sebastian Farquhar +3

Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by…

cs.LG2022★ 19 cited

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Sören Mindermann, Jan Brauner, Muhammed Razzak +8

Training on web-scale data can take months. But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable. To accelerate training,…

cs.AI2022★ 3 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…