Curriculum Vitae
Full name and title for official stuff: Dr. T.A.L. van Erven
Research Interests
In my research group we design mathematically well-founded machine learning methods for online convex optimization that work well out of the box, without any manual fine-tuning. We do this by identifying statistically ‘easy’ situations (e.g. low noise, small norm optimal parameters, etc.) in which it is possible to learn more efficiently, with less data. We then construct adaptive methods that exploit these easy cases when present, but automatically fall back to slower robust learning strategies when there is no easy structure. This is technically challenging, because it typically requires automatic hyper-parameter tuning, for which we develop new approaches.
In addition, we have recently started on a formal mathematical analysis of explainability methods, which explain the black-box decisions made by machine learning systems to a user. In the past I have also worked on topics in information theory, model selection for Bayesian statistics, and PAC-Bayesian concentration inequalities.
Reviewing
- Senior Program Committee member for COLT 2015-2023
- Senior Program Committee member for ALT 2022
- Area Chair for NeurIPS 2018, 2019, 2020
- Reviewer for COLT, NeurIPS, ICML, IEEE Transactions on Information Theory, the Journal of Machine Learning Research, Machine Learning, BNAIC/BeneLearn, etc.
- COLT 2023 Open problems chair
Organizing
| 2023 - present | Member of the board of directors of the association that organizes COLT |
| 2023 - present | Co-chair for the AI & Mathematics initiative |
| 2018 - present | Co-organizing the thematic seminar with current theme machine learning |
| 2017 - 2022 | Organizing the Netherlands N(eur)IPS debriefing |
| 2019 | Co-organizer of the Young European Statisticians workshop on the Theoretical Foundations of Deep Learning |
| 2016 - 2017 | Local arrangements chair for the COLT 2017 machine learning conference in Amsterdam, together with Wouter Koolen |
| 2016 - present | Running the machine learning Nederland mailing list for machine learning in the Netherlands |
| 2015 | Organizer of the workshop Learning Faster from Easy Data II at NIPS 2015. |
| 2008 | Co-organizer of the workshop Recent Breakthroughs in MDL Learning (ICML/UAI/COLT, Helsinki, Finland) |
Memberships
Grants and Awards
| 2019 | VIDI grant by the Dutch Research Council |
| 2016 | TOP grant, compartment 2 by the Dutch Research Council |
| 2014 | NIPS 2014 outstanding reviewer award |
| 2011 | Awarded a Rubicon grant by the Dutch Research Council to do a two-year postdoc in Paris with Pascal Massart |
| 2009 | A preprint of the paper Catching up faster by switching sooner won second prize in the student paper competition of the Risk Analysis Section of the American Statistical Association. |
| ≤ 2006 | Obtained both bachelor's and master's degree cum laude (with honors) |
Teaching
Here is a list of some of the classes I have taught.
Positions and Studies
| 2020 - present | Associate professor in the Korteweg-de Vries Institute for Mathematics at the University of Amsterdam |
| 2014 - 2020 | Assistant professor in the statistics group at Leiden University |
| 2012 - 2014 | Postdoc at Université Paris-Sud in France in the group of Pascal Massart, and member of the INRIA team SELECT |
| 2011 - 2012 | Postdoc at VU University with Aad van der Vaart |
| 2010 - 2011 | Postdoc at CWI with Peter Grünwald |
| 2006 - 2010 | PhD student at CWI under supervision of Peter Grünwald |
| 2005 | Trainee at CWI |
| 2000 - 2006 | Studied Artificial Intelligence at the University of Amsterdam |