Alexander Timans

Mail   |   GitHub   |   Google Scholar   |   LinkedIn   |   CV

I am a PhD student in Machine Learning at the University of Amsterdam supervised by Eric Nalisnick in the Amsterdam Machine Learning Lab. I am also affiliated with the Delta Lab, a research collaboration between the University of Amsterdam and the Bosch Center for Artificial Intelligence. In that context, I am co-supervised by Bosch research scientists Kaspar Sakmann and Christoph-Nikolas Straehle.

My research interests focus on principled and efficient uncertainty quantification for deep learning models, with a particular focus on applications in the computer vision domain. This includes probabilistic approaches such as those relying on Bayesian principles, but also those based on frequentists frameworks such as conformal prediction. I am also interested in the connection to other notions of reliability such as model calibration, robustness and generalization, and interpretability; as well as alternative frameworks providing safety assurances.

I graduated with an MSc in Statistics from ETH Zurich, specialising in machine learning and computational statistics. My master thesis was done as an interdisciplinary project with the Mobility Information Engineering Lab on uncertainty quantification in traffic prediction (see here). I graduated with a BSc in Industrial Engineering and Management from the Karlsruhe Institute of Technology (KIT), focusing on statistics and finance.

profile photo

Updates

Oct 7, 2023: Participated in ICCV 2023 in Paris to present our poster on 'Adaptive Bounding Box Uncertainty via Conformal Prediction' at the Workshop on Uncertainty Quantification in Computer Vision -- thanks to the organizers! It was fun to see the thriving ML community and the various research directions particulary in the computer vision domain. Notably, there was a lot of work on multi-modality and foundation model finetuning. Some interesting thoughts on the current state of the field were given in the Quo Vadis, Computer Vision workshop by the likes of David Forsyth, Bill Freeman and Jitendra Malik -- is "putting language into vision" the best approach? Also got to catch Yann LeCun in person at the Meta booth!

Sep 1, 2023: I was happy to participate in the ELLIS Doctoral Symposium 2023 in Helsinki, Finland! A lot of fun activities (and sauna galore) and great to see so many fellow ML PhD students enthusiastically present their work. Particularly interesting discussions on calibration for regression and conformal prediction for time series -- thanks and maybe see you next year!

Aug 23, 2023: The AMLab yearly retreat was good fun, with karaoke and escape room action as well as plenty of socialising -- I'm happy to be working with such a nice crowd!

Aug 11, 2023: The research paper Uncertainty Quantification for Image-based Traffic Prediction across Cities, a resulting work from my master thesis in collaboration with the Mobility Information Engineering Lab at ETH Zurich, is finally publicly available on arXiv! We will also be aiming for a journal submission.

Aug 9, 2023: Our workshop submission on 'Adaptive Bounding Box Uncertainty via Conformal Prediction' got accepted to the Workshop on Uncertainty Quantification in Computer Vision at ICCV 2023 -- looking forward to presenting our work in Paris!

Aug 1, 2023: My bachelor student Derck Prinzhorn successfully graduated with a thesis on the topic of Benchmarking conformal prediction methods for time series regression -- great job and congratulations!

Apr 4, 2023: Started a bachelor thesis supervision project on conformal prediction for time series, as well as TA'ing the Deep Learning 2 course with a module on uncertainty quantification. I am also supervising a course project on Bayesian subnetwork inference.

Mar 28, 2023: Had an interesting time at the Bosch Center for Artificial Intelligence HQ in Renningen in the context of a lab visit organised by the Delta Lab. It was great to meet my Bosch co-supervisors in person and see about how our research can potentially translate to Bosch applications, such as in autonomous driving and robotics.

Feb 16, 2023: Participated in the CWI Machine Learning Theory Bootcamp just next door to the University campus. I particularly enjoyed the talk by Bob Williamson on imprecise probability.

Oct 10, 2022: Joined the Amsterdam Machine Learning Lab (AMLab) as a PhD candidate supervised by Eric Nalisnick!

Research

Adaptive Bounding Box Uncertainty via Conformal Prediction


Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann, Eric Nalisnick

ICCV 2023 Workshop on Uncertainty Quantification for Computer Vision
Links: Paper

We quantify the uncertainty in multi-object 2D bounding box predictions via conformal prediction, achieving practically useful prediction intervals with guaranteed per-class coverage for the bounding box coordinates.

 project image

Uncertainty Quantification for Image-based Traffic Prediction across Cities


Alexander Timans, Nina Wiedemann, Nishant Kumar, Ye Hong, Martin Raubal

arXiv preprint (under review), 2023
Links: Paper | Code

We explore a series of uncertainty quantification methods on a large-scale image-based traffic dataset spanning multiple cities and time periods, originally featured as a NeurIPS 2021 prediction challenge. Meaningful uncertainty estimates relating to underlying traffic dynamics are recovered by a combination method of deep ensembles and patch-based deviation. In a case study, we then demonstrate how uncertainty estimates can be employed for unsupervised outlier detection on changes in city traffic dynamics.

 project image

Source: adapted from Dharmesh Tailor's fork of Leonid Keselman's fork of John Barron's website.