Hubert Drazkowski

hubert(dot)drazkowski(at)di.ku.dk

I am

a second year PhD fellow in Theoretical Machine Learning at University of Copenhagen
advised by Yevgeny Seldin and Sebastian Weichwald
a member of CoCaLa and DeLTa labs
interested in causal, sequential and interactive

news

Nov 10, 2026	I will be visitng EPFL in November.
Oct 06, 2026	We will present our work in progress: Best of Both Worlds Causal Bandits with Mediator Feedback at EWRL workshop.
Jul 01, 2026	I will present our work in progress: Semi-Adversarial Bandits with Post-Action Context at UAI workshop Causality for Decision Making.
Jun 22, 2026	Attending the Learning Theory Workshop and Summer School in Copenhagen LTSS 2026. Presenting work in progress: Semi-Adversarial Bandits with Post-Action Context.
Jun 03, 2026	Attending the Reinforcement Learning Summer School in Milano RLSS 2026.

selected publications

CLeaR
Oral

Cross-Sectional Conditional Independence in Stationary Time Series: Graphical Equivalence and Completeness of Collider Separation

Hubert Drazkowski

In Conference on Causal Learning and Reasoning (CLeaR), 2026

Abs PDF Slides

Proximal variables regression estimates effects in the presence of unobserved confounding by using conditionally separated proxies. We study a structural violation caused by variables that act simultaneously as mediators and colliders between them.
CLeaR

Beware of Hinges in Proximal Variables Regression: Adjusting for Colliding-Mediators with Nuisance PV

Hubert Drazkowski

In Conference on Causal Learning and Reasoning (CLeaR), 2026

Abs PDF

We study cross-sectional conditional independence in time series. We reconcile two graphical separations and prove for them strong completeness within GaussianVAR.