I am a Research Fellow at the Gatsby Computational Neuroscience Unit at University College London, where I work with Arthur Gretton.

My research focuses on statistical and algorithmic questions in machine learning systems, especially in sequential decision-making, policy learning, and causal inference, with a particular interest in nuisance-robust methods and inference under adaptive data collection.

About Me

Before joining UCL, I was a postdoctoral researcher at INRIA MIND, collaborating with Bertrand Thirion, Judith Abecassis, and Julie Josse. I completed my PhD at INRIA Thoth under the supervision of Julien Mairal, Pierre Gaillard and Eustache Diemert in collaboration with the causal inference group at the Criteo AI Lab.

Prior to that, I received an M.Eng. degree in applied mathematics and computer science from CentraleSupelec and an M.Sc. degree from the MVA program at ENS Paris-Saclay. I also worked at the Institute for Infocomm Research under the supervision of Chuan-Sheng Foo and Vijay Chandrasekhar.

My thesis manuscript is available here, and my CV is available here.

News

• Jan 2026: One paper accepted at AISTATS 2026!

Selected Publications

• Fast Best-in-Class Regret for Contextual Bandits
  S. Girard, A. Bibaut, A. Gretton, N. Kallus, H. Zenati.
  Preprint, 2026.

• Efficient Inference after Directionally Stable Adaptive Experiments
  Z. Shen, H. Zenati, N. Kallus, A. Gretton, K. Khamaru, A. Bibaut.
  Preprint, 2026.
  [arXiv]

• Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings
  Houssam Zenati, Bariscan Bozkurt, Arthur Gretton.
  NeurIPS, 2025.
  [Paper] · [Code]

• Sequential Counterfactual Risk Minimization
  Houssam Zenati, Eustache Diemert, Matthieu Martin, Julien Mairal, Pierre Gaillard.
  ICML, 2023.
  [Paper] · [Code]

• Efficient Kernelized UCB for Contextual Bandits
  Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard.
  AISTATS, 2022.
  [Paper] · [Code]