Welcome to my homepage. I am an associate professor at the Korteweg-de Vries Institute for Mathematics at the University of Amsterdam in the Netherlands. My research is about the mathematical foundations of machine learning.

News

• July 2023: Elected to join the board of directors for COLT
• April 2023: I joined the board of the national AI & Mathematics initiative (AIM)
• Upcoming events:
  • September 14-16, 2023: Attending EWRL 2023 in Brussels
  • October 12, 2023: Giving a 3 hour masterclass about the mathematics of explainable machine learning as part of the 3rd annual meeting for the Dutch inverse problems community in Groningen.
  • October 27, 2023: I will be in Saarbrücken for a workshop on interpretable machine learning
• Recent talks and events:
  • 12-15 July, 2023: talk at COLT 2023 about generalization guarantees via algorithm-dependent Rademacher complexity
  • 19 June, 2023: talked about robust online convex optimization in the presence of outliers in the DeLTA Lab seminar at the University of Copenhagen.
  • June 1-2, 2023: I was part of the organizing team for the Second workshop on AI & Mathematics (AIM) organized by the Dutch Mathematics Clusters. We put together a really cool program with great national speakers.
  • I kicked off the Online learning in complex environments part of the workshop on Game theory for AI organized by the University of Maastricht together with the AI and Mathematics (AIM) initiative, on March 30-31, 2023. Here are the slides.
  • Tutorial about Formal Results in Explainable Machine Learning as part of the CWI Machine Learning Theory Boot Camp on February 14-15, 2023. Here are the slides.

Older News

• We have a series of great international speakers in the Statistics and Machine Learning Thematic Seminar
• I have started blogging again.
• Gave a mini-course with three lectures on adaptive online learning at the ENSAI in Rennes, 17-21 feb, 2020
• Received a VIDI grant from the Dutch Research Council
• Co-organizing the thematic seminar with current theme machine learning
• We had the Young European Statisticians workshop on the Theoretical Foundations of Deep Learning
• Started a mailing list for machine learning in the Netherlands

Research Interests in Mathematical Machine Learning

• The mathematics of explainable machine learning
• Adaptive methods in online convex optimization and prediction with expert advice
• Faster-than-minimax rates for ‘easy data’ in statistical and online learning
• PAC-Bayesian concentration inequalities
• Statistical learning theory, frequentist analysis of Bayesian methods

See also my publications.

Selected Talks

• Talks about our impossibility result in explainable machine learning. Slides are here:
  • December 16, 2022, at the University of Amsterdam, SIAS @ LAB42
  • November 23, 2022, at the University of Tübingen, Germany
  • October 5, 2022, at the Symposium on Transparent Machine Learning organised by the Vereniging voor Statistiek en Operations Research (VVSOR).
  • October 3, 2022, in the Probability & Statistics seminar at the TU Delft.
• Introduction to (distributed) online learning at the Young European Queueing Theorists workshop, Nov 2 - Nov 4, 2022. Slides are here.
• High-level talk about the relation between Statistics and Machine Learning in the Netherlands at the 1st AI & Mathematics workshop at CWI, June 9-10, 2022.
• Opening talk giving an introduction to online learning at the CWI-INRIA 2019 workshop
• Invited talk with some highlights in online convex optimization in the machine learning session at the Netherlands Mathematical Congress, 2018
• Invited talks in Toulouse, Delft, Rennes, Leuven, Poznań and Amsterdam, 2017-2018, about using multiple learning rates in online learning with MetaGrad to automatically adapt to the best possible learning rate. A related tutorial introduction to adaptive online learning at ABN AMRO, Amsterdam, 2018.
• Invited talk at Inria Lille, 2017, about fast rates in statistical and online learning. Also gave this talk in the Thematic Seminar 2018.
• Talked about MetaGrad, a new adaptive online optimization method, at the Theoretical Foundations for Learning from Easy Data workshop in Leiden, 2016
• Invited talk in the WIC Midwintermeeting 2016 on Big Data and Data Analytics
• Presented my work with Wouter Koolen on automatically learning the learning rate parameter in online learning at Benelearn 2015 and for the Leiden Centre of Data Science
• Introduction to Online Learning for a general mathematical audience in the Leiden Mathematics Colloquium, 2014
• Presented an open problem in the Online Algorithms and Learning international workshop in Leiden, 2014
• Talk about Follow the Leader with Dropout Perturbations at COLT 2014 in Barcelona
• Invited talk on convergence of the MDL estimator in the session on Model Selection in Statistical Learning at the ERCIM conference in Londen, December 14, 2013
• Invited talk about Follow the Leader If You Can, Hedge If You Must in the Learning Faster from Easy Data workshop at NIPS in Lake Tahoe, USA, December 10, 2013
• Making Regional Forecasts Add Up at the WIPFOR workshop in Paris, June 6, 2013
• The Catch-up Phenomenon in Bayesian and MDL Model Selection in the “Bayes in Paris” seminar, May 23, 2013
• Invited lecture giving An Introduction to Online Learning for Bayesians at the University of Amsterdam, February 15, 2013
• Mixability in Statistical Learning in the SMILE seminar in Paris, September 24, 2012

Contact Information

Dr. Tim van Erven
Korteweg-de Vries Institute for Mathematics
University of Amsterdam
P.O. Box 94248
1090 GE Amsterdam
The Netherlands

Visiting address:
Science Park 107, 3rd floor (entrance via Nikhef)
Office: F3.32