Publications

Most of my publications are in alphabetical order unless specified otherwise (notation: *equal contribution).

2026

  1. NeurIPS
    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. NeurIPS
    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. COLT
    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
    arXiv HTML PDF
  4. COLT
    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
    arXiv HTML PDF
  5. ICML
    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
    arXiv HTML PDF

2025

  1. NeurIPS
    When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses
    Antoine Moulin*, Emmanuel Esposito*, and Dirk van der Hoeven
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arXiv HTML PDF
  2. ICML
    Exploiting Curvature in Online Convex Optimization with Delayed Feedback
    Hao Qiu*, Emmanuel Esposito*, and Mengxiao Zhang*
    Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025
    arXiv HTML PDF
  3. COLT
    A Fine-grained Characterization of PAC Learnability
    Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, and Maximilian Thiessen
    Proceedings of the 38th Conference on Learning Theory (COLT), 2025
    HTML PDF
  4. COLT
    Of Dice and Games: A Theory of Generalized Boosting
    Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, and Maximilian Thiessen
    Proceedings of the 38th Conference on Learning Theory (COLT), 2025
    arXiv HTML PDF
  5. JAIR
    Improved Regret Bounds for Bandits with Expert Advice
    Nicolò Cesa-Bianchi, Khaled Eldowa, Emmanuel Esposito, and Julia Olkhovskaya
    Journal of Artificial Intelligence Research, 2025
    DOI arXiv HTML
  6. IPL
    An Improved Uniform Convergence Bound with Fat-Shattering Dimension
    Roberto Colomboni, Emmanuel Esposito, and Andrea Paudice
    Information Processing Letters, 2025
    DOI arXiv HTML

2024

  1. COLT
    A Theory of Interpretable Approximations
    Marco Bressan, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, and Maximilian Thiessen
    Proceedings of the 37th Conference on Learning Theory (COLT), 2024
    arXiv HTML PDF
  2. COLT
    Efficient Algorithms for Learning Monophonic Halfspaces in Graphs
    Marco Bressan, Emmanuel Esposito, and Maximilian Thiessen
    Proceedings of the 37th Conference on Learning Theory (COLT), 2024
    arXiv HTML PDF

2023

  1. NeurIPS
    Spotlight Paper
    On the Minimax Regret for Online Learning with Feedback Graphs
    Khaled Eldowa*, Emmanuel Esposito*, Tommaso Cesari, and Nicolò Cesa-Bianchi
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    Spotlight arXiv HTML PDF
  2. ICML
    Delayed Bandits: When Do Intermediate Observations Help?
    Emmanuel Esposito*, Saeed Masoudian*, Hao Qiu, Dirk van der Hoeven, Nicolò Cesa-Bianchi, and Yevgeny Seldin
    Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
    arXiv HTML

2022

  1. NeurIPS
    Learning on the Edge: Online Learning with Stochastic Feedback Graphs
    Emmanuel Esposito*, Federico Fusco*, Dirk van der Hoeven*, and Nicolò Cesa-Bianchi
    Advances in Neural Information Processing Systems (NeurIPS), 2022
    arXiv HTML

2020

  1. ALENEX
    RecSplit: Minimal Perfect Hashing via Recursive Splitting
    Emmanuel Esposito, Thomas Mueller Graf, and Sebastiano Vigna
    2020 Proceedings of the Symposium on Algorithm Engineering and Experiments (ALENEX), 2020
    DOI arXiv HTML Code