Emmanuel Esposito

Postdoc at FairPlay, CREST, ENSAE
Email: emmanuel [at] emmanuelesposito [dot] it

me.png

I am Postdoctoral Researcher in the FairPlay team at CREST, ENSAE, hosted by Vianney Perchet. Previously, was a Postdoctoral Researcher in the LAILA lab at the University of Milan. I obtained my PhD in Computer Science at the University of Milan and the Italian Institute of Technology, where I was fortunate to be supervised by Nicolò Cesa-Bianchi and Massimiliano Pontil.

My research interests broadly lie in Online Learning and Machine Learning Theory. One of the key focuses of my research is to understand the interplay between feedback models and the hardness of sequential decision-making problems. I am also generally interested in their intersection with other areas of machine learning, such as Reinforcement Learning, Game Theory, and Optimization.

news

Sep 22, 2023 Our paper “On the Minimax Regret for Online Learning with Feedback Graphs” (arXiv) has been accepted as a Spotlight at NeurIPS 2023. See you in New Orleans!
Sep 12, 2023 Our ICML 2023 paper has been accepted at EWRL 2023. See you in Brussels!
Sep 08, 2023 I’ll be visiting the University of Amsterdam.

selected publications

  1. Strongly Adaptive Online Learning with Time-Varying Movement Costs
    Andrew Jacobsen, Emmanuel Esposito, Hao Qiu, and Mengxiao Zhang
    Advances in Neural Information Processing Systems (NeurIPS), 2026
  2. Generalized Adaptive Boosting and the Geometry of Mistakes
    Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, and Maximilian Thiessen
    Advances in Neural Information Processing Systems (NeurIPS), 2026
  3. Learning Conditional Averages
    Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, and Maximilian Thiessen
    Conference on Learning Theory (COLT), 2026
  4. Active Learning on Adversarially Corrupted Graphs
    Marco Bressan, Nicolò Cesa-Bianchi, Tommaso D’Orsi, Emmanuel Esposito, and Silvio Lattanzi
    Conference on Learning Theory (COLT), 2026
  5. Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
    Hao Qiu*, Andrew Jacobsen*, Emmanuel Esposito*, and Mengxiao Zhang*
    International Conference on Machine Learning (ICML), 2026