Sebastian Farquhar | DeepAI

AI Chat

Featured Co-authors

Yoshua Bengio
448 publications
Yarin Gal
126 publications
Jie Ren
66 publications
Kevin Murphy
62 publications
Jacob Steinhardt
58 publications
Balaji Lakshminarayanan
51 publications
Tom Rainforth
49 publications
Dustin Tran
42 publications
Been Kim
42 publications
Rodolphe Jenatton
36 publications
Jasper Snoek
34 publications

∙ 05/24/2023

Model evaluation for extreme risks

Current approaches to building general-purpose AI systems tend to produc...

0 Toby Shevlane, et al. ∙

∙ 04/17/2023

Prediction-Oriented Bayesian Active Learning

Information-theoretic approaches to active learning have traditionally f...

0 Freddie Bickford Smith, et al. ∙

∙ 02/19/2023

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

We introduce a method to measure uncertainty in large language models. F...

0 Lorenz Kuhn, et al. ∙

∙ 12/15/2022

CLAM: Selective Clarification for Ambiguous Questions with Large Language Models

State-of-the-art language models are often accurate on many question-ans...

0 Lorenz Kuhn, et al. ∙

∙ 11/11/2022

Do Bayesian Neural Networks Need To Be Fully Stochastic?

We investigate the efficacy of treating all the parameters in a Bayesian...

0 Mrinank Sharma, et al. ∙

∙ 11/11/2022

Understanding Approximation for Bayesian Inference in Neural Networks

Bayesian inference has theoretical attractions as a principled framework...

0 Sebastian Farquhar, et al. ∙

∙ 08/17/2022

Discovering Agents

Causal models of agents have been used to analyse the safety aspects of ...

0 Zachary Kenton, et al. ∙

∙ 06/14/2022

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

Training on web-scale data can take months. But most computation and tim...

12 Sören Mindermann, et al. ∙

∙ 04/21/2022

Path-Specific Objectives for Safer Agent Incentives

We present a general framework for training safe agents whose naive ince...

0 Sebastian Farquhar, et al. ∙

∙ 02/16/2022

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

Pruning neural networks at initialization would enable us to find sparse...

0 Milad Alizadeh, et al. ∙

∙ 02/14/2022

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

We propose Active Surrogate Estimators (ASEs), a new method for label-ef...

3 Jannik Kossen, et al. ∙

∙ 07/06/2021

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

We introduce Goldilocks Selection, a technique for faster model training...

5 Sören Mindermann, et al. ∙

∙ 06/22/2021

A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions

In active learning, new labels are commonly acquired in batches. However...

5 Andreas Kirsch, et al. ∙

∙ 06/07/2021

Uncertainty Baselines: Benchmarks for Uncertainty Robustness in Deep Learning

High-quality estimates of uncertainty and robustness are crucial for num...

0 Zachary Nado, et al. ∙

∙ 03/09/2021

Active Testing: Sample-Efficient Model Evaluation

We introduce active testing: a new framework for sample-efficient model ...

0 Jannik Kossen, et al. ∙

∙ 01/27/2021

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

Active learning is a powerful tool when labelling data is expensive, but...

0 Sebastian Farquhar, et al. ∙

∙ 07/01/2020

Single Shot Structured Pruning Before Training

We introduce a method to speed up training by 2x and inference by 3x in ...

13 Joost van Amersfoort, et al. ∙

∙ 02/10/2020

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

We challenge the longstanding assumption that the mean-field approximati...

13 Sebastian Farquhar, et al. ∙

∙ 12/22/2019

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

Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...

86 Angelos Filos, et al. ∙

∙ 07/01/2019

Radial Bayesian Neural Networks: Robust Variational Inference In Big Models

We propose Radial Bayesian Neural Networks: a variational distribution f...

7 Sebastian Farquhar, et al. ∙

∙ 02/18/2019

Differentially Private Continual Learning

Catastrophic forgetting can be a significant problem for institutions th...

6 Sebastian Farquhar, et al. ∙

∙ 02/18/2019

A Unifying Bayesian View of Continual Learning

Some machine learning applications require continual learning - where da...

10 Sebastian Farquhar, et al. ∙

∙ 05/24/2018

Towards Robust Evaluations of Continual Learning

Continual learning experiments used in current deep learning papers do n...

2 Sebastian Farquhar, et al. ∙

∙ 02/20/2018

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

This report surveys the landscape of potential security threats from mal...

3 Miles Brundage, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world