research
∙
05/24/2023
Model evaluation for extreme risks
Current approaches to building general-purpose AI systems tend to produc...
share
research
∙
04/17/2023
Prediction-Oriented Bayesian Active Learning
Information-theoretic approaches to active learning have traditionally f...
research
∙
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...
research
∙
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...
research
∙
11/11/2022
Do Bayesian Neural Networks Need To Be Fully Stochastic?
We investigate the efficacy of treating all the parameters in a Bayesian...
research
∙
11/11/2022
Understanding Approximation for Bayesian Inference in Neural Networks
Bayesian inference has theoretical attractions as a principled framework...
research
∙
08/17/2022
Discovering Agents
Causal models of agents have been used to analyse the safety aspects of ...
research
∙
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...
research
∙
04/21/2022
Path-Specific Objectives for Safer Agent Incentives
We present a general framework for training safe agents whose naive ince...
research
∙
02/16/2022
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
Pruning neural networks at initialization would enable us to find sparse...
research
∙
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...
research
∙
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...
research
∙
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...
research
∙
06/07/2021
Uncertainty Baselines: Benchmarks for Uncertainty Robustness in Deep Learning
High-quality estimates of uncertainty and robustness are crucial for num...
research
∙
03/09/2021
Active Testing: Sample-Efficient Model Evaluation
We introduce active testing: a new framework for sample-efficient model ...
research
∙
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...
research
∙
07/01/2020
Single Shot Structured Pruning Before Training
We introduce a method to speed up training by 2x and inference by 3x in ...
research
∙
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...
research
∙
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...
research
∙
07/01/2019
Radial Bayesian Neural Networks: Robust Variational Inference In Big Models
We propose Radial Bayesian Neural Networks: a variational distribution f...
research
∙
02/18/2019
Differentially Private Continual Learning
Catastrophic forgetting can be a significant problem for institutions th...
research
∙
02/18/2019
A Unifying Bayesian View of Continual Learning
Some machine learning applications require continual learning - where da...
research
∙
05/24/2018
Towards Robust Evaluations of Continual Learning
Continual learning experiments used in current deep learning papers do n...
research
∙
02/20/2018
