MDL
1 July 2021 to 17 December 2021
Due to the massive amounts of training data complemented by a tremendously increased computing power, deep neural networks have recently seen an impressive comeback. In fact, we currently witness how algorithms based on deep neural networks are infusing numerous aspects of the public sector such as being used for pre-screening job applications or revolutionizing the healthcare industry. A similarly strong impact can be observed on science itself. Deep learning based approaches have proven very useful within certain mathematical problem settings such as solving ill-posed inverse problems or high-dimensional partial differential equations, sometimes already leading to state-of-the-art algorithms. However, most of the related research is still empirically driven and a sound theoretical foundation is largely missing. This is not only a significant problem from a scientific viewpoint, but particularly critical for sensitive applications such as in the health care sector. Thus there exists a tremendous need for mathematics of deep learning.
Aiming to derive a mathematical foundation of deep learning, this programme addresses theoretical questions in two realms:
1) Theoretical foundations of deep learning independent of a particular application.
(2) Theoretical analysis of the potential and the limitations of deep learning for mathematical methodologies, in particular, for inverse problems and partial differential equations.
Area (1) focusses on the area of expressivity asking how powerful network architecture is from an approximation viewpoint, on the area of learning aiming to rigorously mathematically analyse training algorithms, and on the area of generalization to understand the ability of neural networks to perform well on out-of-sample data also. Those three research directions originate from the viewpoint of statistical learning. In addition, our programme aims to study questions related to interpretability, security, and safety of deep learning.
Area (2) focusses on the application of deep neural networks to solve ill-posed inverse problems and partial differential equations. Key research goals in this regime are understanding how deep learning can be optimally combined with model-based methods as well as complete mathematical error analyses for such deep learning based approximation algorithms for ill-posed inverse problems or high-dimensional partial differential equations which reveal the success and the limitations of such algorithms when applied to such mathematical problems.
The main goal of this programme is to achieve substantial progress in developing a theoretical foundation of deep learning. For this, the programme will for the first time gather the top experts from various areas of mathematics and of the theory of machine learning, including computer scientists, physicists, and statisticians in one place, initiating collaborations across intra- and interdisciplinary boundaries and thereby generating unprecedented research dynamics.
> Click here to see the content produced by Plus Magazine during the MDL programme
Click here to download the programme's final scientific report
9 August 2021 to 13 August 2021
27 September 2021 to 1 October 2021
15 November 2021 to 19 November 2021
22 November 2021 to 23 November 2021
13 December 2021 to 15 December 2021
28 February 2022 to 4 March 2022
The Organisers would like to thank the following sponsors for their generous support of the event:
Tuesday 20th July 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Matthew Thorpe University of Manchester |
Room 1 | |
Wednesday 21st July 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Petar Veličković University of Cambridge |
Room 1 |
Wednesday 28th July 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Simon Arridge University College London |
Room 2 | |
17:00 to 18:30 |
Eldad Haber University of British Columbia |
Room 2 |
Tuesday 3rd August 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Clarice Poon University of Bath |
Room 1 | |
Wednesday 4th August 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Tatiana Alessandra Bubba University of Cambridge |
Room 1 |
Thursday 5th August 2021 | |||
---|---|---|---|
13:00 to 13:15 |
Ralf Korn Technische Universität Kaiserslautern |
Room 1 | |
13:15 to 14:00 |
Ralf Korn Technische Universität Kaiserslautern |
Room 1 | |
14:00 to 14:45 |
Robert Sicks Technische Universität Kaiserslautern |
Room 1 | |
15:00 to 15:45 |
Fatlinda Avdullai Technische Universität Kaiserslautern |
Room 1 | |
15:45 to 16:30 |
Simon Schnürch University of Kaiserslautern |
Room 1 | |
16:30 to 17:15 |
Magnus Wiese University of Kaiserslautern |
Room 1 |
Tuesday 17th August 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Guido Montufar Max-Planck-Institut für Mathematik, Leipzig; University of California, Los Angeles |
Room 1 | |
Wednesday 18th August 2021 | |||
---|---|---|---|
17:00 to 18:30 |
George Karniadakis Brown University |
Room 1 |
Monday 23rd August 2021 | |||
---|---|---|---|
10:00 to 11:00 |
Michael Bronstein |
Room 1 | |
Tuesday 24th August 2021 | |||
---|---|---|---|
10:00 to 11:00 |
Michael Bronstein |
Room 1 | |
Wednesday 25th August 2021 | |||
---|---|---|---|
10:00 to 11:00 |
Michael Bronstein |
Room 1 | |
17:00 to 18:30 |
Ferdia Sherry University of Cambridge |
Room 1 |
Wednesday 1st September 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Andrew Stuart CALTECH (California Institute of Technology) |
Room 1 |
Tuesday 14th September 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Carola-Bibiane Schönlieb University of Cambridge; Cambridge Mathematics of Information in Healthcare |
Room 1 | |
Wednesday 15th September 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Matthias Ehrhardt University of Bath |
Room 2 |
Tuesday 21st September 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Martin Burger Universität Erlangen-Nürnberg |
Room 2 | |
Wednesday 22nd September 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Po-Ling Loh University of Cambridge |
Room 2 |
Thursday 23rd September 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Weinan E Princeton University |
Room 2 | |
14:00 to 15:00 |
Weinan E Princeton University |
Room 2 | |
Friday 24th September 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Weinan E Princeton University |
Room 2 | |
Tuesday 5th October 2021 | |||
---|---|---|---|
09:00 to 10:30 |
Ivan Tyukin University of Leicester |
Room 1 | |
Wednesday 6th October 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Yury Korolev University of Cambridge |
Room 1 |
Tuesday 12th October 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Jong Chul Ye Korea Advanced Institute of Science and Technology (KAIST) |
Room 1 | |
Wednesday 13th October 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Robert Nowak University of Wisconsin-Madison; Toyota Technological Institute |
Room 2 |
Monday 18th October 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Sebastian Neumayer Technische Universität Berlin |
Room 1 |
Tuesday 19th October 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Sebastian Neumayer Technische Universität Berlin |
Room 1 | |
Wednesday 20th October 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Anna Korba ENSAE (École Nationale de la Statistique et de l'Administration) |
Room 2 |
Monday 25th October 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Matthew Thorpe University of Manchester |
Room 1 |
Tuesday 26th October 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Matthew Colbrook University of Cambridge |
Room 1 | |
Wednesday 27th October 2021 | |||
---|---|---|---|
16:00 to 17:00 |
Rebecca Willett University of Chicago |
Room 1 | |
16:30 to 18:30 |
Rama Cont University of Oxford |
Discussion Room |
Monday 1st November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Alexandru Cioba MediaTek Research |
Room 1 | |
Tuesday 2nd November 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Brynjulf Owren Norwegian University of Science and Technology |
Room 2 | |
Wednesday 3rd November 2021 | |||
---|---|---|---|
16:00 to 17:30 |
Jeremy Budd Delft University of Technology |
Room 2 |
Monday 8th November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Malena Sabaté Landman Cambridge Mathematics of Information in Healthcare |
Room 2 | |
Tuesday 9th November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Lexing Ying Stanford University |
Room 2 | |
Wednesday 10th November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Lexing Ying Stanford University |
Room 2 | |
17:00 to 18:30 |
Qin Li University of Wisconsin-Madison |
Room 2 |
Thursday 11th November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Lexing Ying Stanford University |
Room 2 | |
Wednesday 24th November 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Soheil Kolouri |
Room 2 |
Monday 29th November 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Tamara Grossmann University of Cambridge |
Room 2 |
Tuesday 30th November 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Nina Gottschling Cambridge Centre for Analysis |
Room 2 |
Wednesday 1st December 2021 | |||
---|---|---|---|
17:00 to 18:30 |
Christoph Schwab ETH Zürich |
Room 2 |
Friday 3rd December 2021 | |||
---|---|---|---|
16:00 to 17:00 | Room 1 |
Monday 6th December 2021 | |||
---|---|---|---|
14:00 to 15:00 |
Margaret Duff University of Bath |
Room 1 | |
Tuesday 7th December 2021 | |||
---|---|---|---|
09:00 to 10:00 |
Anna Kerekes Centre for Mathematical Sciences |
Room 2 | |
Wednesday 8th December 2021 | |||
---|---|---|---|
15:00 to 16:00 | Room 1 | |
|
17:00 to 18:30 |
Christopher Budd University of Bath |
Room 2 |
Friday 10th December 2021 | |||
---|---|---|---|
10:00 to 11:00 |
Helmut Bölcskei ETH Zürich |
Room 1 | |
16:00 to 17:00 |
Helmut Bölcskei ETH Zürich |
Room 1 | |
Subscribe for the latest updates on events and news
Isaac Newton Institute for Mathematical Sciences, 20 Clarkson Road, Cambridge CB3 0EH United Kingdom
Tel: +44 1223 335999 Email: reception@newton.ac.uk
© 2023 Isaac Newton Institute for Mathematical Sciences. All Rights Reserved. Privacy Policy
INI is a creative collaborative space which is occupied by up to fifty-five mathematical scientists at any one time (and many more when there is a workshop). Some of them may not have met before and others may not realise the relevance of other research to their own work.
INI is especially important as a forum where early-career researchers meet senior colleagues and form networks that last a lifetime.
Here you can learn about all activities past, present and future, watch live seminars and submit your own proposals for research programmes.
Within this section of the website you should find all the information required to arrange and plan your visit to the Institute. If you have any further questions, or are unable to find the information you require, please get in touch with the relevant staff member or our Reception team via our contact pages.
INI and its programme participants produce a range of publications to communicate information about activities and events, publish research outcomes, and document case studies which are written for a non-technical audience. You will find access to them all in this section.
The Isaac Newton Institute aims to maximise the benefit of its scientific programmes to the UK mathematical science community in a variety of ways.
Whether spreading research opportunities through its network of correspondents, offering summer schools to early career researchers, or hosting public-facing lectures through events such as the Cambridge Festival, there is always a great deal of activity to catch up on.
Find out about all of these endeavours in this section of the site.
There are various ways to keep up-to-date with current events and happenings at the Isaac Newton Institute. As detailed via the menu links within this section, our output covers social media streams, news articles, a regular podcast series, an online newsletter, and more detailed documents produced throughout the year.
“A world famous place for research in the mathematical sciences with a reputation for efficient management and a warm welcome for visitors”
The Isaac Newton Institute is a national and international visitor research institute. It runs research programmes on selected themes in mathematics and the mathematical sciences with applications over a wide range of science and technology. It attracts leading mathematical scientists from the UK and overseas to interact in research over an extended period.
INI has a vital national role, building on many strengths that already exist in UK universities, aiming to generate a new vitality through stimulating and nurturing research throughout the country.During each scientific programme new collaborations are made and ideas and expertise are exchanged and catalysed through lectures, seminars and informal interaction, which the INI building has been designed specifically to encourage.
For INI’s knowledge exchange arm, please see the Newton Gateway to Mathematics.
The Institute depends upon donations, as well as research grants, to support the world class research undertaken by participants in its programmes.
Fundraising activities are supported by a Development Board comprising leading figures in academia, industry and commerce.
Visit this section to learn more about how you could play a part in supporting INI’s groundbreaking research.
In this section you can find contact information, staff lists, maps and details of how to find INI’s main building in Cambridge.
Our administrative staff can help you with any queries regarding a prospective or planned visit. If you would like to discuss a proposed a research programme or other event, our senior management team will be happy to help.