Search Results for author:
Found 19 papers, 13 papers with code
Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models
Diffusion models have shown promising potential for advancing Boltzmann Generators.
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community.
A Generative Model of Symmetry Transformations
Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge.
Stochastic Gradient Descent for Gaussian Processes Done Right
We study the use of stochastic gradient descent for solving this linear system, and show that when \emph{done right} -- by which we mean using specific insights from the optimisation and kernel communities -- stochastic gradient descent is highly effective.
SE(3) Equivariant Augmented Coupling Flows
Coupling normalizing flows allow for fast sampling and density evaluation, making them the tool of choice for probabilistic modeling of physical systems.
Online Laplace Model Selection Revisited
The Laplace approximation provides a closed-form model selection objective for neural networks (NN).
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
Gaussian processes are a powerful framework for quantifying uncertainty and for sequential decision-making but are limited by the requirement of solving linear systems.
Image Reconstruction via Deep Image Prior Subspaces
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.
Sampling-based inference for large linear models, with application to linearised Laplace
Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the linearised Laplace method.
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction.
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community.
Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior
Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment.
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not
Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance.
Depth Uncertainty Networks for Active Learning
In active learning, the size and complexity of the training dataset changes over time.
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders.
Bayesian Deep Learning via Subnetwork Inference
In particular, we implement subnetwork linearized Laplace as a simple, scalable Bayesian deep learning method: We first obtain a MAP estimate of all weights and then infer a full-covariance Gaussian posterior over a subnetwork using the linearized Laplace approximation.
Depth Uncertainty in Neural Networks
Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited.
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems.
Variational Depth Search in ResNets
One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost.
