Research output per year
Research output per year
Personal profile
Overview
I have two main research interests: The first is in the application of methods from the calculus of variations to analyse large data limits of problems that arise from machine learning and statistics. The second is in the application and development of optimal transport distances to signal and image analysis.
Currently I am a co-organiser for the One World Seminar Series on the Mathematics of Machine Learning, an editor for the journal Foundations of Data Science and a fellow at the Alan Turing Institute.
I am also a part of the Cambridge led project on AI assisted diagnosis and prognostication in Covid-19, and the European Union's Horizon 2020 program NoMADS (grant agreement number 777826).
I would be happy to discuss potential PhD projects, particularly in the area of connecting differential equations with neural networks (both for the analysis of nueral networks and to design better neural network architectures). The ideal background for this work would include (at least some of) metric spaces, measure theory, functional analysis and calculus of variations. Coding experience is a positive but not necessary. Please reach out if you would like to talk more.
Further information
I can be contacted at matthew[dot]thorpe[dash]2@manchester[dot]ac[dot]uk.
Between the 1st July 2021 and 17th December I will be visiting the Isaac Newton Institute programme on the Mathematics of Deep Learning. Most days I can be found in office F2 in the INI building.
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
External positions
Research Fellow, University of Cambridge
1 Sep 2017 → 29 Feb 2020
Postdoctoral Associate, Carnegie Mellon University
1 Sep 2015 → 31 Aug 2017
Research Beacons, Institutes and Platforms
- Digital Futures
Keywords
- Machine Learning
- Calculus of Variations
- Statistics
- Optimal Transport
Fingerprint
Dive into the research topics where Matthew Thorpe is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
-
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans
Roberts, M., Driggs, D., Thorpe, M., Gilbey, J., Yeung, M., Ursprung, S., Aviles-Rivero, A., Etmann, C., McCague, C., Beer, L., Weir-McCall, J., Teng, Z., Gkrania-Klotsas, E., AIX-COVNET, Rudd, J., Sala, E. & Schoenlieb, C-B., 15 Mar 2021, In: Nature Machine Intelligence. 3, p. 199-217Research output: Contribution to journal › Article › peer-review
Open Access -
Robust Certification for Laplace Learning on Geometric Graphs
Thorpe, M. & Wang, B., 2021, Proceedings of Machine Learning Research.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
Large Data and Zero Noise Limits of Graph-Based Semi-Supervised Learning Algorithms
Dunlop, M., Slepcev, D., Stuart, A. M. & Thorpe, M., Sep 2020, In: Applied and Computational Harmonic Analysis. 49, 2, p. 655-697 43 p.Research output: Contribution to journal › Article › peer-review
Open AccessFile82 Downloads (Pure) -
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
Calder, J., Cook, B., Thorpe, M. & Slepcev, D., 2020, Proceedings of the International Conference on Machine Learning. p. 8588--8598Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
Analysis of p-Laplacian Regularization in Semi-Supervised Learning
Slepcev, D. & Thorpe, M., 23 May 2019, In: SIAM Journal on Mathematical Analysis . 51, 3, p. 2085-2120Research output: Contribution to journal › Article › peer-review
Open Access
Projects
- 1 Active
-
Centre for Digital Trust and Society
Barrett, E., Allmendinger, R., Elliot, M., Lord, N., Cordeiro, L., Gibson, R., Papamarkou, T., Dresner, D., Buil Gil, D., Aldridge, J., Duncan, P., Banach, R., Brown, G., Dennis, L., Fisher, M., Korovin, K., Kotselidis, C., Luján, M., Mustafa, M., Olivier, P., Reger, G., Zhang, N., Hodgkinson, G., Gulati, S., Ainsworth, J., Chen, Y., Green, B., Healey, M., Uyarra, E., Zachariadis, M., Little, C., Mackey, E., Nenadic, G., Keane, J., Shlomo, N., Laskowski, N., Jarwar, M. A., Shariati Samani, S., Smith, D., Kambites, M., Thorpe, M., Rowley, P., Flynn, S., Turner, P., Wainwright, V., Czerwinsky, A., Nini, A., Broad, R., Shute, J., Deakin, J., Taboada, P., Knight, P., Hutchings, S., Whyte, J., Tolz-Zilitinkevic, V., Pilkington, H., Guharoy, S., Nicolo, A., Reggiani, C., Garcia Oliva, J., Van Someren, A., Bon, E., Cantijoch Cunill, M., Koch, D. & Chen, Y.
11/05/21 → …
Project: Other