Teo Deveney

According to our database, Teo Deveney authored at least 7 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

G-Adaptive mesh refinement - leveraging graph neural networks and differentiable finite element solvers.

James Rowbottom, Georg Maierhofer, Teo Deveney, Katharina Schratz, Pietro Liò, Carola-Bibiane Schönlieb, Chris J. Budd

CoRR, 2024

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks.

Simone Appella, Simon R. Arridge, Chris J. Budd, Teo Deveney, Lisa Maria Kreusser

CoRR, 2024

Diffusion Models Encode the Intrinsic Dimension of Data Manifolds.

Jan Stanczuk, Georgios Batzolis, Teo Deveney, Carola-Bibiane Schönlieb

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Deep Surrogate Accelerated Delayed-Acceptance Hamiltonian Monte Carlo for Bayesian Inference of Spatio-Temporal Heat Fluxes in Rotating Disc Systems.

Teo Deveney, Eike Hermann Müller, Tony Shardlow

SIAM/ASA J. Uncertain. Quantification, September, 2023

Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation.

Teo Deveney, Jan Stanczuk, Lisa Maria Kreusser, Chris J. Budd, Carola-Bibiane Schönlieb

CoRR, 2023

2022

Deep surrogate accelerated delayed-acceptance HMC for Bayesian inference of spatio-temporal heat fluxes in rotating disc systems.

Teo Deveney, Eike Hermann Müller, Tony Shardlow

CoRR, 2022

2019

A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models.

Teo Deveney, Eike Hermann Müller, Tony Shardlow

CoRR, 2019