41 citations · 96 across the 18 of their papers we have counts for
19 papers
DFT Accuracy on Crystal Structure Prediction with Machine Learning Interatomic Potentials
Laurence I. Midgley, Chen Lin, J. Harry Moore +8
We present an evaluation of CSP-MACE-Å, a machine learning interatomic potential intended to replace DFT in crystal structure prediction (CSP). We decompose the total energy into s…
Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models
Fengzhe Zhang, Jiajun He, Laurence I. Midgley +2
Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfecti…
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec +2
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community. This paper focuses on iterative methods, which use linear syst…
A Generative Model of Symmetry Transformations
James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy +5
Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require…
Stochastic Gradient Descent for Gaussian Processes Done Right
Jihao Andreas Lin, Shreyas Padhy, Javier Antorán +5
As is well known, both sampling from the posterior and computing the mean of the posterior in Gaussian process regression reduces to solving a large linear system of equations. We…
SE(3) Equivariant Augmented Coupling Flows
Laurence I. Midgley, Vincent Stimper, Javier Antorán +3
Coupling normalizing flows allow for fast sampling and density evaluation, making them the tool of choice for probabilistic modeling of physical systems. However, the standard coup…
Online Laplace Model Selection Revisited
Jihao Andreas Lin, Javier Antorán, José Miguel Hernández-Lobato
The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, lik…
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
Jihao Andreas Lin, Javier Antorán, Shreyas Padhy +3
Gaussian processes are a powerful framework for quantifying uncertainty and for sequential decision-making but are limited by the requirement of solving linear systems. In general,…
Image Reconstruction via Deep Image Prior Subspaces
Riccardo Barbano, Javier Antorán, Johannes Leuschner +3
Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised l…
Sampling-based inference for large linear models, with application to linearised Laplace
Javier Antorán, Shreyas Padhy, Riccardo Barbano +3
Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the…
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
Riccardo Barbano, Johannes Leuschner, Javier Antorán +2
We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach…
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antorán, David Janz, James Urquhart Allingham +4
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and a…
Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior
Javier Antorán, Riccardo Barbano, Johannes Leuschner +2
Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment. This p…
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not
Chelsea Murray, James U. Allingham, Javier Antorán +1
Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as N…
Depth Uncertainty Networks for Active Learning
Chelsea Murray, James U. Allingham, Javier Antorán +1
In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active…
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Umang Bhatt, Javier Antorán, Yunfeng Zhang +12
Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most…
Depth Uncertainty in Neural Networks
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato
Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limi…
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel +2
Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems. However, there is little work at the intersection of these two area…
Variational Depth Search in ResNets
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato
One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost. We limit our search space to the depth of residual netwo…