X Close

UKRI Centre for Doctoral Training in Foundational AI



Archive for October, 2022

Conference on Learning Theory COLT 2022 by Antonin Schrab

By sharon.betts, on 14 October 2022

Professor Benjamin Guedj standing at podium at COLT 22

« COLT has been the prime annual meeting of the growing learning theory community for 35 years now, and that London edition has been beyond our expectations. We have been planning COLT 2022 since late 2019, and due to Covid it was unclear until a few weeks before the conference how many people would be able or willing to join. Our optimistic scenario was 150 on site attendees — we ended up at more than 270! COLT 2022 featured the higher number ever of papers (155) in a dual track format. I am especially proud that over 50% of attendees were MSc, PhD and postdocs: COLT has long been a welcoming and inclusive forum for early-career researchers. As local chair, COLT has eaten up a lot of my days and nights recently, but it certainly was worth it! » Benjamin GuedjInria and University College London, COLT 2022 Local Chair.

This July, I’ve had the great pleasure of participating in the Conference on Learning Theory COLT 2022 which has been held in person in London! I found the conference to be a real success, it was wonderful to finally be able to meet so many people sharing the same interests in learning theory! It was amazing to follow talks held in the historic Royal Institution of Great Britain which is the location of the famous televised Christmas Lectures!

The conference kicked off with a joint workshop between COLT and IMS (Institute of Mathematical Statistics) Annual Meeting with tutorials and talks by Emmanuel CandèsNati Srebro and Vladimir Vovk on the topics of conformal prediction and mathematics of deep learning. This workshop allowed to bring together both audience (IMS and COLT) with aligned interests on statistics and learning theory. This was a great initiative which was really appreciated by all the participants I talked to, I hope the joint workshop between IMS and COLT will remain in future editions of the conferences!

During the four following days, all papers accepted to COLT 2022 have been presented by the authors. Each talk was ten minutes long, this format allowed to get a good overview of each of the 155 papers. Topics included Online Learning, Statistics, Privacy, Robustness, Computational Complexity, Deep Learning, Generalization, Bandits, Sampling, Optimization, Graphs, Information Theory, Reinforcement Learning and Control. It was also very interesting to listen to longer talks such as those of the two papers which received the best paper and best student paper awards of COLT 2022 (Efficient Convex Optimization Requires Superlinear Memory by Annie Marsden, Vatsal Sharan, Aaron Sidford, and Gregory Valiant, and New Projection-Free Algorithms for Online Convex Optimization with Adaptive Regret Guarantees by Ben Kretzu and Dan Garber), as well as those given by plenary speakers: Jelani Nelson from Berkeley, University of CaliforniaMaryam Fazel from University of Washington, and Alon Orlitsky from University of California San Diego.

I also really enjoyed the open problem sessions in which unsolved problems were presented in the hope that these can be solved in future editions of COLT, it was great to see which learning theory problems people currently find challenging! Other events were also organised such as the LeT-All career panel providing advice to early researchers, the Women in Machine Learning Theory luncheon discussing everyday challenges women are facing in academic and industrial Machine Learning research, the business meeting with COLT announcements about future editions of the conference, the workshop reception and the conference gala dinner which were the perfect opportunity to engage with other participants!

COLT 2022 was made possible thanks to the hard-working organizing committee: program chair Po-Ling Loh from University of Cambridge, program chair Maxim Raginsky from University of Illinois at Urbana-Champaign, local chair Benjamin Guedj from Inria and University College London, local chair Ciara Pike-Burke from Imperial College London, open problems chair Clément Canonne from University of Sydney, online experience chair Claire Vernade from DeepMind, and publication chair Suriya Gunasekar from Microsoft Research. Thank you all for making COLT 2022 possible and such a success!

I am now looking forward to COLT 2023!

Blog: DeepMind/ELLIS CSML Seminar Series 2021/2022 by Antonin Schrab

By sharon.betts, on 3 October 2022


I have been delighted to be in charge of organising the DeepMind/ELLIS CSML Seminar Series 2021/2022 for the second year in a row. The aim of this seminar series is to foster collaboration across different UCL departments of the UCL ELLIS Unit (previously Computational Statistics and Machine Learning, CSML) which include the Gatsby Computational Neuroscience Unit, the Centre for Artificial Intelligence, the Department of Computer Science, the Department of Statistical Science, and the Department of Electronic and Electrical Engineering. Talks topics cover some of the latest research in Machine Learning and Statistics. All information about the seminar series can be found online, recordings are available on YouTube, talks are advertised on Twitter, on a mailing list and on a calendar.

Due to the sanitary situation, we have held our seminars online for the first half of the academic year, this allowed to host international speakers from across the globe. For the second half of the academic year, we were able to resume in-person seminars and to host speakers at UCL. We are immensely grateful to DeepMind for sponsoring our seminar series, allowing us to also host speakers from outside of London. I’d also like to thank all the speakers for presenting their latest work at our seminar series during this 2021/2022 academic year, all talks are presented below. Finally, I’d like to thank Jean KaddourOscar KeyPierre Glaser and Azhir Mahmood for their help in hosting the seminars, and I am very excited to welcome Kai Teh from the UCL Department of Statistical Science and Mathieu Alain from the UCL Centre for Artificial Intelligence who will join me in co-organising the seminar series for the 2022/2023 academic year!