4.4k citations · 6.2k across the 79 of their papers we have counts for
88 papers
Learnable Splines for Unstructured Neural Operators
Vignesh Gopakumar, Zhuoyuan Wang, Ander Gray +12
Neural operators approximate solution operators of partial differential equations at a fraction of the cost of numerical solvers. Efficient grid-based architectures such as the Fou…
Learning Physical Operators using Neural Operators
Vignesh Gopakumar, Ander Gray, Dan Giles +5
Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are ofte…
Infinite Neural Operators: Gaussian processes on functions
Daniel Augusto de Souza, Yuchen Zhu, Harry Jake Cunningham +3
A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over their outputs. These relationships provide both…
Calibrated Physics-Informed Uncertainty Quantification
Vignesh Gopakumar, Ander Gray, Lorenzo Zanisi +5
Simulating complex physical systems is crucial for understanding and predicting phenomena across diverse fields, such as fluid dynamics and heat transfer, as well as plasma physics…
Learning Dynamic Tasks on a Large-scale Soft Robot in a Handful of Trials
Sicelukwanda Zwane, Daniel Cheney, Curtis C. Johnson +4
Soft robots offer more flexibility, compliance, and adaptability than traditional rigid robots. They are also typically lighter and cheaper to manufacture. However, their use in re…
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Fabian Paischer, Lukas Hauzenberger, Thomas Schmied +3
Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common fine-tuning method is to update pretrained weigh…
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang +1
Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must…
Uncertainty Quantification of Surrogate Models using Conformal Prediction
Vignesh Gopakumar, Ander Gray, Joel Oskarsson +5
Data-driven surrogate models offer quick approximations to complex numerical and experimental systems but typically lack uncertainty quantification, limiting their reliability in s…
Valid Error Bars for Neural Weather Models using Conformal Prediction
Vignesh Gopakumar, Joel Oskarrson, Ander Gray +5
Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do…
RDM: Recurrent Diffusion Model for Human Motion Generation
Mirgahney Mohamed, Harry Jake Cunningham, Marc P. Deisenroth +2
Human motion generation is a challenging task due to its high dimensionality and the difficulty of generating fine-grained motions. Diffusion methods have been proposed due to thei…
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Joel Oskarsson, Tomas Landelius, Marc Peter Deisenroth +1
In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on determinist…
Scalable Data Assimilation with Message Passing
Oscar Key, So Takao, Daniel Giles +1
Data assimilation is a core component of numerical weather prediction systems. The large quantity of data processed during assimilation requires the computation to be distributed a…
Iterated INLA for State and Parameter Estimation in Nonlinear Dynamical Systems
Rafael Anderka, Marc Peter Deisenroth, So Takao
Data assimilation (DA) methods use priors arising from differential equations to robustly interpolate and extrapolate data. Popular techniques such as ensemble methods that handle…
Plasma Surrogate Modelling using Fourier Neural Operators
Vignesh Gopakumar, Stanislas Pamela, Lorenzo Zanisi +10
Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. Capabilities in forecasting the spatio-temporal evolution of plasma rap…
Gaussian Processes on Cellular Complexes
Mathieu Alain, So Takao, Brooks Paige +1
In recent years, there has been considerable interest in developing machine learning models on graphs to account for topological inductive biases. In particular, recent attention h…
Thin and Deep Gaussian Processes
Daniel Augusto de Souza, Alexander Nikitin, ST John +6
Gaussian processes (GPs) can provide a principled approach to uncertainty quantification with easy-to-interpret kernel hyperparameters, such as the lengthscale, which controls the…
A Unifying Variational Framework for Gaussian Process Motion Planning
Lucas Cosier, Rares Iordan, Sicelukwanda Zwane +5
To control how a robot moves, motion planning algorithms must compute paths in high-dimensional state spaces while accounting for physical constraints related to motors and joints,…
Faster Training of Neural ODEs Using Gauß-Legendre Quadrature
Alexander Norcliffe, Marc Peter Deisenroth
Neural ODEs demonstrate strong performance in generative and time-series modelling. However, training them via the adjoint method is slow compared to discrete models due to the req…
Grasp Transfer based on Self-Aligning Implicit Representations of Local Surfaces
Ahmet Tekden, Marc Peter Deisenroth, Yasemin Bekiroglu
Objects we interact with and manipulate often share similar parts, such as handles, that allow us to transfer our actions flexibly due to their shared functionality. This work addr…
Neural Field Movement Primitives for Joint Modelling of Scenes and Motions
Ahmet Tekden, Marc Peter Deisenroth, Yasemin Bekiroglu
This paper presents a novel Learning from Demonstration (LfD) method that uses neural fields to learn new skills efficiently and accurately. It achieves this by utilizing a shared…
Sliding Touch-based Exploration for Modeling Unknown Object Shape with Multi-fingered Hands
Yiting Chen, Ahmet Ercan Tekden, Marc Peter Deisenroth +1
Efficient and accurate 3D object shape reconstruction contributes significantly to the success of a robot's physical interaction with its environment. Acquiring accurate shape info…
On Combining Expert Demonstrations in Imitation Learning via Optimal Transport
Ilana Sebag, Samuel Cohen, Marc Peter Deisenroth
Imitation learning (IL) seeks to teach agents specific tasks through expert demonstrations. One of the key approaches to IL is to define a distance between agent and expert and to…
Implicit regularisation in stochastic gradient descent: from single-objective to two-player games
Mihaela Rosca, Marc Peter Deisenroth
Recent years have seen many insights on deep learning optimisation being brought forward by finding implicit regularisation effects of commonly used gradient-based optimisers. Unde…
Investigating the Edge of Stability Phenomenon in Reinforcement Learning
Rares Iordan, Marc Peter Deisenroth, Mihaela Rosca
Recent progress has been made in understanding optimisation dynamics in neural networks trained with full-batch gradient descent with momentum with the uncovering of the edge of st…