News
Back to page: home.
April 25, 2025 New Preprint: First paper on SBI. We integrate the latest foundation model for tabular data, TabPFN, for the use of Bayesian inference, specifically for SBI.
arXiv Code
Dezember 11, 2024, SBI hackathon: We organize a hackathon on the SBI toolbox that we maintain. The hackathon is remote and on-site at the University of Tübingen during 17-21 March 2025.
SBI website details
September 15, 2024, Postdoc: I started my postdoc at the Mackelab as part of the Tübingen AI center at the University of Tübingen, Germany.
June 14, 2024, Ph.D.: I successfully defended my Ph.D. thesis “On Deep Learning for Low-Dimensional Representations”.
pdf DiVA slides
May 2, 2024, Accepted Paper: Our high-dimensional analysis paper got accepted to ICML. We study the combination of Principal Component Analysis (PCA) with linear regression on data from a spiked covariance model to provide precise asymptotic guarantees for the risk.
OpenReview ICML code poster
April 26, 2024, Accepted Paper: Our work on integrating Recursive Feature Machines (RFMs) into Gaussian Processes was accepted at UAI. We show that the resulting GP-RFM is a strong alternative to existing SOTA methods for tabular regression problems.
OpenReview code poster
November 6, 2023, Accepted Paper: The first work from my research visit at Misha Belkins Lab at UCSD was accepted at the UniReps workshop at NeurIPS. We studied the emergence of similar representations in Recursive Feature Machines and in GPs with Automatic Relevance Determination.
OpenReview NeurIPS workshop poster
September 30, 2023, Accepted Paper: Our MSc students work on ECG-based risk prediction was published at the Journal of Electrocardiography. Congrats, Theogene!
doi arXiv code models
July 4, 2023, Accepted Paper: Another work ours using ECGs + deep learning got accepted at PLOS Neglected Tropical Diseases. We show that deep learning models can be used to detect Chagas disease from ECGs, aiding in early detection.
doi medRxiv code models
June 28, 2023, Invited Talk: A talk on our preprint survey paper of deep networks for system identification got accepted at the 2023 ERNSI workshop in Stockholm. We got a main presentation slot of 1h.
slides workshop arXiv
May 11, 2023, Accepted Paper: Our paper on invertible kernel PCA got accepted at IEEE Signal Processing Letters. We present a simple but effective method to invert the kernel PCA operations in an invertible subdomain which is sufficient for reconstruction in many scenarios.
doi arXiv code
January 03, 2023, Research Visit: I will visit Misha Belkin’s group at UC San Diego from 1st of March to 27th of May. During that time we will work on generalization of overparameterized models.
Misha Belkin
December 05, 2022, Poster Presentation: I presented a poster on our ongoing work in ECG-regression for electrolyte prediction at the annual AI4Reserach workshop, Uppsala.
poster workshop
November 22, 2022, Invited Talk: The bi-annual joint meeting from the Swedish and Danish societies for biopharmaceutical/medical statistics (DSBS, FMS), invited me to talk about our latest work in prediction models for myocardial infarctions from ECGs.
program slides
November 16, 2022, DDLS Panel Discussion: I was invited to a panel talk at the DDLS Annual Conference at SciLifeLab in Stockholm. The panel discussion has the topic: Training in Data Driven Life Science.
program conference
November 15, 2022, Paper Accepted: Our paper with the title “Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients” was accepted for publication at Scientific Reports.
doi
July 25, 2022, Workshop Participation: Next week from 01.08-05.08 I will participate in the “Deep Learning Theory Workshop and Summer School” at the Simons Institute for the Theory of Computing. This will be my first in-person event since the start of my PhD.
workshop
June 02, 2022, Master Defence - Theogene: My master student Theogene Habineza defended his master thesis titled “Risk Prediction of Atrial Fibrillation Using the 12-lead ECG”. The reviewer was Thomas Schön.
March 25, 2022, Half-Time Seminar: I presented my PhD half-time seminar titled “Deep models for temporal data with applications to electrocardiography”.
details slides
February 23, 2022, Pedagogical Video: We created a video on explaining the essence of machine learning in a pedagogical way with a medical classification example.
project video blog
October 26, 2021, Accepted Paper: Our submission in ECG classification of myocardial infarctions to the NeurIPS workshop “Machine learning from ground truth: New medical imaging datasets for unsolved medical problems Workshop” was accepted as spotlight talk.
paper slides workshop
Back to page: home.