Machine Learning in Infinite Dimensions
Bath, 5-9 August 2024

Photo by Ferla Paolo Photography

Description

Lifting high-dimensional problems to an infinite-dimensional space and designing algorithms in that setting has been a fruitful idea in many areas of applied mathematics, including inverse problems, optimisation, and partial differential equations. This approach is sometimes referred to as "optimise-then-discretise" and allows the development of algorithms that are inherently dimension- and discretisation-independent and can perform better in high-dimensions. In the context of machine learning, this paradigm can be rephrased as "learn-then-discretise".

The Machine Learning in Infinite Dimensions workshop aims to bring together researchers that work on different aspects of infinite-dimensionality in machine learning. Topics include, but are not restricted to, Gaussian process regression, operator learning, function spaces of neural networks, and measure transport. 

Confirmed speakers

• Ricardo Baptista (California Institute of Technology)

• Nicolas Boullé (University of Cambridge/Imperial College London)

• Christoph Brune (University of Twente)

• Andrew B Duncan (Imperial College London)

• Jean Feydy (INRIA)

• Manuela Girotti (Emory University)

• Sophie Langer (University of Twente)

• Caroline Moosmueller (University of North Carolina at Chapel Hill)

• Nicole Mücke (Technical University of Braunschweig)

• Nicholas Nelsen (California Institute of Technology/Massachusetts Institute of Technology)

• Sebastian Neumayer (Chemnitz University of Technology)

• Domènec Ruiz-Balet (Imperial College London)

• Cong Shi (University of  Vienna)

• Christoph Schwab (ETH Zürich)

• Gabriele Steidl (Technical University of  Berlin)

• Marius Zeinhofer (Freiburg University Hospital)

Organisers

Tatiana Bubba (University of Bath)

Bamdad Hosseini (University of Washington)

Yury Korolev (University of Bath)

Matthew Thorpe (University of Warwick)