I am a Research Fellow at the Gatbsy Computationaly Neuroscience Unit at the University College of London working under the supervision of Arthur Gretton.

Prior to that, I was postdoc at the INRIA Mind working with Bertrand Thirion, Judith Abecassis and Julie Josse at the INRIA PreMedical team.

My thesis manuscript was on Efficient methods in counterfactual policy learning and sequential decision making.

I did my PhD at INRIA Thoth under the supervision of Julien Mairal and Pierre Gaillard in collaboration with the causal inference research group at the Criteo AI Lab. My research interests lie in the interface of counterfactual reasoning and online learning algorithms.

Prior to that, I received a M.Eng. degree in applied mathematics and computer science from CentraleSupelec as well as the MVA M.Sc. degree from ENS Paris-Saclay.

Previously, I also worked at the Institute for Infocomm Research under the supervision of Chuan-Sheng Foo and Vijay Chandrasekhar.

You can find my CV here.

I also like hiking, traveling and learning Japanese, as you may see here.

News

• Feb 2025: My work on counterfactual policy learning with continuous actions has been accepted at TMLR!
• Janv 2025: My work on mediation analysis with continuous treatments has been accepted at AISTATS2025!
• Janv 2025: I have been given the opportunity to work at Gatbsy!

Publications

Journal papers

Counterfactual Learning of Stochastic Policies with Continuous Actions

Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Pierre Gaillard, Julien Mairal

Transactions on Machine Learning Research, 2025

[Paper] [Code]

## _Conference papers_

Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments

Houssam Zenati, Judith Abecassis, Julie Josse, and Bertrand Thirion.

International Conference on Artificial Intelligence and Statistics, 2025

[Paper]

Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits

Julien Zhou, Thibaud Rahier, Julyan Arbel, Houssam Zenati, and Pierre Gaillard.

Neural Information Processing Systems, 2024

[Paper]

Sequential Counterfactual Risk Minimization

Houssam Zenati, Eustache Diemert, Matthieu Martin, Julien Mairal, Pierre Gaillard

International Conference on Machine Learning, 2023

[Paper] [Code]

Nested Bandits

Matthieu Martin, Panagiotis Mertikopoulos, Thibaud Rahier, Houssam Zenati

International Conference on Machine Learning, 2022

[Paper] [Code]

Efficient Kernelized UCB for Contextual Bandits

Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard

International Conference on Artificial Intelligence and Statistics, 2022

[Paper] [Code]

Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile

Panagiotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar and Georgios Piliouras

International Conference on Learning Representation, 2019

[Paper]

Adversarially Learned Anomaly Detection

Houssam Zenati, Manon Romain, Chuan-Sheng Foo, Bruno Lecouat, Vijay Chandrasekhar

International Conference on Data Mining, 2019

[Paper] [Code]

## _Workshop papers_

Optimization approaches for counterfactual risk minimization with continuous actions

Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Julien Mairal

International Conference on Learning Representation, Causal Learning for Decision Making Workshop, 2020

[Paper] [Code]

Towards practical unsupervised anomaly detection on retinal images

Khalil Ouardini, Huijuan Yang, Balagopal Unnikrishnan, Manon Romain, Camille Garcin, Houssam Zenati, J Peter Campbell, Michael F Chiang, Jayashree Kalpathy-Cramer, Vijay Chandrasekhar, Pavitra Krishnaswamy, Chuan-Sheng Foo.

International Conference on Medical Image Computing and Computer Assisted Intervention Workshop, 2019

[Paper]

Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images

Bruno Lecouat, Ken Chang, Chuan-Sheng Foo, Balagopal Unnikrishnan, James Brown, Houssam Zenati, Andrew Beers, Vijay Chandrasekhar, Jayashree Kalpathy-Cramer and Pavitra Krishnaswamy.

Neural Information Processing Systems, ML4H Workshop 2018

[Paper]

Semi-Supervised Learning With GANs: Revisiting Manifold Regularization

Bruno Lecouat, Chuan Sheng Foo, Houssam Zenati, Vijay Chandrasekhar

International Conference on Learning Representation Workshop, 2018

[Paper] [Code]

Efficient GAN Based Anomaly Detection

Houssam Zenati, Bruno Lecouat, Chuan Sheng Foo, Gaurav Manek, Vijay Chandrasekhar

[Paper] [Code]