Search Results for author:
Found 44 papers, 12 papers with code
Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces
Touch and vision go hand in hand, mutually enhancing our ability to understand the world.
Batch size invariant Adam
We propose a batch size invariant version of Adam, for use in large-scale, distributed settings, in which the mini-batch is divided into micro-batches which are distributed among worker nodes.
Bayesian Reward Models for LLM Alignment
To ensure that large language model (LLM) responses are helpful and non-toxic, we usually fine-tune a reward model on human preference data.
Flexible infinite-width graph convolutional networks and the importance of representation learning
A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed.
Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets.
TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing
To address these challenges, we propose TouchSDF, a Deep Learning approach for tactile 3D shape reconstruction that leverages the rich information provided by a vision-based tactile sensor and the expressivity of the implicit neural representation DeepSDF.
LoRA ensembles for large language model fine-tuning
To address these issues, we propose an ensemble approach using Low-Rank Adapters (LoRA), a parameter-efficient fine-tuning technique.
Convolutional Deep Kernel Machines
Recent work (A theory of representation learning gives a deep generalisation of kernel methods, Yang et al. 2023) modified the Neural Network Gaussian Process (NNGP) limit of Bayesian neural networks so that representation learning is retained.
Signatures of Bayesian inference emerge from energy efficient synapses
The resulting networks revealed a tradeoff between circuit performance and the energetic cost of synaptic reliability.
Bayesian Low-rank Adaptation for Large Language Models
Low-rank adaptation (LoRA) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs).
An Improved Variational Approximate Posterior for the Deep Wishart Process
When the distribution is chosen to be Wishart, the model is called a deep Wishart process (DWP).
Massively Parallel Reweighted Wake-Sleep
Attaining such a large number of importance samples is intractable in all but the smallest models.
MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning
In Bayesian optimisation, we often seek to minimise the black-box objective functions that arise in real-world physical systems.
Decision trees compensate for model misspecification
These perform well in the presence of complex interactions, with tree depth governing the order of interactions.
Imitating careful experts to avoid catastrophic events
RL is increasingly being used to control robotic systems that interact closely with humans.
Machine learning emulation of a local-scale UK climate model
This work demonstrates the effectiveness of diffusion models, a form of deep generative models, for generating much more cheaply realistic high resolution rainfall samples for the UK conditioned on data from a low resolution simulation.
Random initialisations performing above chance and how to find them
Neural networks trained with stochastic gradient descent (SGD) starting from different random initialisations typically find functionally very similar solutions, raising the question of whether there are meaningful differences between different SGD solutions.
What deep reinforcement learning tells us about human motor learning and vice-versa
We therefore tested three major families of modern deep RL algorithm on a mirror reversal perturbation.
Robustness to corruption in pre-trained Bayesian neural networks
We develop ShiftMatch, a new training-data-dependent likelihood for robustness to corruption in Bayesian neural networks (BNNs).
Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear
In addition, the unsheared tactile images give a faithful reconstruction of the contact geometry that is not possible from the sheared data, and robust estimation of the contact pose that can be used for servo control sliding around various 2D shapes.
A theory of representation learning gives a deep generalisation of kernel methods
In particular, we show that Deep Gaussian processes (DGPs) in the Bayesian representation learning limit have exactly multivariate Gaussian posteriors, and the posterior covariances can be obtained by optimizing an interpretable objective combining a log-likelihood to improve performance with a series of KL-divergences which keep the posteriors close to the prior.
A variational approximate posterior for the deep Wishart process
We develop a doubly-stochastic inducing-point inference scheme for the DWP and show experimentally that inference in the DWP can improve performance over doing inference in a DGP with the equivalent prior.
InfoNCE is variational inference in a recognition parameterised model
In particular, we show that in the infinite sample limit, and for a particular choice of prior, the actual InfoNCE objective is equal to the ELBO (up to a constant); and the ELBO is equal to the marginal likelihood with a deterministic recognition model.
Data augmentation in Bayesian neural networks and the cold posterior effect
Here, we provide several approaches to developing principled Bayesian neural networks incorporating data augmentation.
BNNpriors: A library for Bayesian neural network inference with different prior distributions
Bayesian neural networks have shown great promise in many applications where calibrated uncertainty estimates are crucial and can often also lead to a higher predictive performance.
Variational Laplace for Bayesian neural networks
We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-network weights.
Bayesian OOD detection with aleatoric uncertainty and outlier exposure
In particular, aleatoric uncertainty signals a specific type of OOD point: one without a well-defined class-label, and our model of data curation gives a likelihood for these points, giving us a mechanism for conditioning on outlier points and thus performing principled Bayesian outlier exposure.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Bayesian Neural Network Priors Revisited
Isotropic Gaussian priors are the de facto standard for modern Bayesian neural network inference.
Gradient Regularisation as Approximate Variational Inference
Variational inference in Bayesian neural networks is usually performed using stochastic sampling which gives very high-variance gradients, and hence slow learning.
Variational Laplace for Bayesian neural networks
We develop variational Laplace for Bayesian neural networks (BNNs) which exploits a local approximation of the curvature of the likelihood to estimate the ELBO without the need for stochastic sampling of the neural-network weights.
Deep kernel processes
We show that the deep inverse Wishart process gives superior performance to DGPs and infinite BNNs on standard fully-connected baselines.
Legally grounded fairness objectives
Recent work has identified a number of formally incompatible operational measures for the unfairness of a machine learning (ML) system.
A statistical theory of cold posteriors in deep neural networks
To get Bayesian neural networks to perform comparably to standard neural networks it is usually necessary to artificially reduce uncertainty using a "tempered" or "cold" posterior.
Semi-supervised learning objectives as log-likelihoods in a generative model of data curation
We currently do not have an understanding of semi-supervised learning (SSL) objectives such as pseudo-labelling and entropy minimization as log-likelihoods, which precludes the development of e. g. Bayesian SSL.
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
We consider the optimal approximate posterior over the top-layer weights in a Bayesian neural network for regression, and show that it exhibits strong dependencies on the lower-layer weights.
Why bigger is not always better: on finite and infinite neural networks
Recent work has argued that neural networks can be understood theoretically by taking the number of channels to infinity, at which point the outputs become Gaussian process (GP) distributed.
A unified theory of adaptive stochastic gradient descent as Bayesian filtering
We formulate stochastic gradient descent (SGD) as a novel factorised Bayesian filtering problem, in which each parameter is inferred separately, conditioned on the corresopnding backpropagated gradient.
Deep Convolutional Networks as shallow Gaussian Processes
For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very few parameters: only the hyperparameters of the original CNN.
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients.
Tensor Monte Carlo: particle methods for the GPU era
Multi-sample, importance-weighted variational autoencoders (IWAE) give tighter bounds and more accurate uncertainty estimates than variational autoencoders (VAE) trained with a standard single-sample objective.
Discrete flow posteriors for variational inference in discrete dynamical systems
Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e. g. factorised) approximate posteriors in which sampling is an efficient computation that fully exploits GPU parallelism.
Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit
Population activity measurement by calcium imaging can be combined with cellular resolution optogenetic activity perturbations to enable the mapping of neural connectivity in vivo.
Fast Sampling-Based Inference in Balanced Neuronal Networks
Multiple lines of evidence support the notion that the brain performs probabilistic inference in multiple cognitive domains, including perception and decision making.
Synaptic plasticity as Bayesian inference
They then use that uncertainty to adjust their learning rates, with more uncertain weights having higher learning rates.
