Jeroen Berrevoets

PhD from the University of Cambridge (DAMTP) (member of the vanderschaar-lab, supervised by prof. Mihaela van der Schaar.). My research is focused on causality and machine learning, often applied to medicine. Previously I’ve spent time at VUB, KU Leuven, University of Copenhagen, and BMW Group. If you want to reach out, please send an email to jeroen [dot] berrevoets [at] maths.cam.ac.uk.

[twitter] [scholar] [github] [linkedin]

🗞️ News

• Jan 2024 → Three papers accepted! ✌️👆 A first at TMLR on treatment effects distributions (the last one of 2023 🎆) [paper], one at ICLR24 on ODEs and treatment effects as a spotlight (top 5%)! 🔦 [preprint coming soon], and a third at AISTATS24 on data-centric AI with structure learning [preprint coming soon].

• Sept 2023 → A new paper accepted at NeurIPS23 (D&B)! This one shows how one can structure and simulate counterfactual resource allocation settings. I can’t wait to revisit New Orleans once again to present it 🐊🎺🌶️! (Preprint coming soon)

• Apr 2023 → Two papers accepted at ICML23!! 🌺🌺 A first on structure learning where we reintroduce transportability in differentiable methods [preprint]. A second on relaxing structural assumptions in multi-view learning for tabular data [preprint]. I (really 🏝️🥥) look forward to attend ICML this year!

• Mar 2023 → 🤩 I am incredibly excited to finally share our view on Causal Deep Learning in a new paper we uploaded to the ArXiv [preprint]. We discuss our view with a panel including Cheng Zhang (Microsoft), Guillermo Sapiro (Apple & Duke), and Simon Woodhead (Eedi), have a look on YouTube 📺.

• Jan 2023 → Two papers accepted! 🥳 One at AISTATS23 ([paper]) and one at ICLR23 which is a first time for me ([paper]). I look forward presenting these with my co-authors!

• Dec 2022 → Thrilled to be part of the organising team for the 2nd conference on Causal Learning and Reasoning (CLeaR) 2023. Causality is becoming a major field in machine learning, and CLeaR is going to be its premier conference! Have a look at cclear.cc for more info.

• Aug 2022 → On September 7 I am giving a talk with Zhaozhi Qian at the AI and Machine Learning in Healthcare Summer School organised by CCAIM on causal deep learning, a topic I am very excited about! Have a look at the total program here: https://ccaim.cam.ac.uk/program/.

• Aug 2022 → I am co-organising a NeurIPS 2022 workshop on Causality for Real-world Impact with Nick Pawlowski (Microsoft), Cheng Zhang (Microsoft), Kun Zhang (CMU), Caroline Uhler (MIT), and Mihaela van der Schaar (Cambridge). For more info, please browse to the workshop website.

🧪 Research updated: Jan '24

Please find some of my publications below (a more complete list can be found on google scholar).

* means equal contribution.

Conferences

• J. Berrevoets*, S. Holt*, K. Kacprzyk*, Z. Qian, M. van der Schaar. ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference. ICLR, 2024 spotlight: top 5% [preprint coming soon]
• J. Berrevoets*, N. Huynh*, N. Seedat, J. Crabbé, Z. Qian, M. van der Schaar. DAGnosis: Localized Identification of Data Inconsistencies using Structures. AISTATS, 2024 [preprint coming soon]
• J. Berrevoets, D. Jarrett, A. Chan, M. van der Schaar. AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems. NeurIPS (D&B), 2023. [paper] [code]
• J. Berrevoets, N. Seedat, F. Imrie, M. van der Schaar. Differentiable and Transportable Structure Learning. ICML, 2023. [paper] [code]
• T. Liu, J. Berrevoets, Z. Qian, M. van der Schaar. Learning Representations Without Compositional Assumptions. ICML, 2023. [paper] [code]
• J. Berrevoets, F. Imrie, T. Kyono, J. Jordon, M. van der Schaar. To Impute or not to Impute? Missing Data in Treatment Effect Estimation. AISTATS, 2023. [paper] [code]
• T. Liu, Z. Qian, J. Berrevoets, M. van der Schaar. GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure. ICLR, 2023. [paper] [code]
• J. Berrevoets*, Y. Zhang*, M. van der Schaar. Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects. AISTATS, 2022. [paper] [code]
• B. van Breugel*, T. Kyono*, J. Berrevoets, M. van der Schaar. DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks. NeurIPS, 2021. [paper] [code]
• J. Berrevoets, A. Alaa, Z. Qian, J. Jordon, A. Gimson, M. van der Schaar. Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis. ICML, 2021. [paper] [code]
• J. Berrevoets, J. Jordon, I. Bica, A. Gimson, M. van der Schaar. OrganITE: Optimal Transplant Donor Organ Offering Using an Individual Treatment Effect. NeurIPS, 2020. [paper] [code]
• J. Berrevoets, S. Verboven, W. Verbeke. Optimising Individual-Treatment-Effect Using Bandits. CausalML workshop at NeurIPS, 2019. [paper] [code]

Journals

• T. Vanderschueren, J. Berrevoets, W. Verbeke. NOFLITE: Learning to Predict Individual Treatment Effect Distributions. Transactions on Machine Learning Research (TMLR), 2023 [paper]
• J. Berrevoets, S. Verboven, W. Verbeke. Treatment Effect Optimisation in Dynamic Environments. Journal of Causal Inference, 2022. [paper]
• S. Verboven, M.H. Chaudhary, J. Berrevoets, V. Ginis, W. Verbeke. HydaLearn: Highly Dynamic Task Weighting for Multitask Learning with Auxiliary Tasks. Applied Intelligence, 2022. [paper]
• F. Devriendt, J. Berrevoets, W. Verbeke. Why you should stop predicting customer churn and start using uplift models. Information Sciences, 2021. [paper]
• S. Verboven, J. Berrevoets, C. Wuytens, B. Baesens, W. Verbeke. Autoencoders for Strategic Decision Support. Decision Support Systems, 2020. [paper]

Preprints

• J. Berrevoets, K. Kacprzyk, Z. Qian, M. van der Schaar. Causal deep learning. 2023. [preprint]
• T. Hatt, J. Berrevoets, A. Curth, S. Feuerriegel, M. van der Schaar. Combining observational and randomized data for estimating heterogeneous treatment effects. 2022. [preprint]
• J. Berrevoets, A. Curth, I. Bica, M. van der Schaar. Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time. 2021. [preprint]
• W. Verbeke, D. Olaya, J. Berrevoets, S. Verboven, S. Maldonado. The foundations of cost-sensitive causal classification. 2020. [preprint]