47 citations · 143 across the 21 of their papers we have counts for
7 papers · 1 filter
Rethinking Aleatoric and Epistemic Uncertainty
Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope +3
The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discu…
Amortized Active Causal Induction with Deep Reinforcement Learning
Yashas Annadani, Panagiotis Tigas, Stefan Bauer +1
We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not req…
Making Better Use of Unlabelled Data in Bayesian Active Learning
Freddie Bickford Smith, Adam Foster, Tom Rainforth
Fully supervised models are predominant in Bayesian active learning. We argue that their neglect of the information present in unlabelled data harms not just predictive performance…
Prediction-Oriented Bayesian Active Learning
Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar +3
Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BA…
Differentiable Multi-Target Causal Bayesian Experimental Design
Yashas Annadani, Panagiotis Tigas, Desi R. Ivanova +4
We introduce a gradient-based approach for the problem of Bayesian optimal experimental design to learn causal models in a batch setting -- a critical component for causal discover…
Learning Instance-Specific Augmentations by Capturing Local Invariances
Ning Miao, Tom Rainforth, Emile Mathieu +4
We introduce InstaAug, a method for automatically learning input-specific augmentations from data. Previous methods for learning augmentations have typically assumed independence b…
Improving Transformation Invariance in Contrastive Representation Learning
Adam Foster, Rattana Pukdee, Tom Rainforth
We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance a…