Bio

I am a Senior Lecturer (equiv. to Assistant Professor) at Tel Aviv University. My research is in Machine Learning Theory, with connections to probability theory, game theory, statistics, complexity, privacy and applied machine learning.

I was a Postdoctoral Researcher at UC Berkeley, studying learning theory under the Machine Learning Pod of Simons Institute and the Foundations of Data Science Institute (FODSI). I received a PhD from the Electrical Engineering and Computer Science department at MIT, advised by Prof. Constantinos Daskalakis. I received George M. Sprowls PhD Thesis award In Artificial Intelligence and Decision Making. I am a recipient of the Facebook Research Fellowship for the years 2021-2022. I received Bachelor’s and Master’s degrees from the Technion, Israel, advised by Prof. Yuval Filmus.

Email: [email protected]

CV

Students

For a Master’s degree: Angelos Assos (Co-advised with Constantinos Daskalakis, MIT); Rui Yao (Helped Daskalakis with advising, MIT); Maya Baruch; Amnon Levy; Lior Ben Yaakov; Uri Aviad; Sivan Khermosh; Nadav Eisen (TAU)

PhD students that I guided as a more senior collaborator (among others): Vardis Kandiros, Maxwell Fishelson

Publications

  • Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Robert Kleinberg, Princewill Okoroafor. Breaking the $T^{2/3}$ Barrier for Sequential Calibration. STOC 2025. Invited for submission to STOC 2025 Special Issue.
  • Angelos Assos, Yuval Dagan, Nived Rajaraman. Intractability of Strategizing against Online Learners. COLT 2025.
  • Angelos Assos, Yuval Dagan, Constantinos Daskalakis. Maximizing utility in multi-agent environments by anticipating the behavior of other learners. NeurIPS 2024
  • Yuval Dagan, Michael I. Jordan, Xuelin Yang, Lydia Zakynthinou, Nikita Zhivotovskiy. Dimension-free Private Mean Estimation for Anisotropic Distributions. NeurIPS 2024.
  • From External to Swap Regret 2.0: An Efficient Reduction and Oblivious Adversary for Large Action Spaces. Yuval Dagan, Constantinos Daskalakis, Noah Golowich, Maxwell Fishelson. Lecture about this paper by Natalie Collina in a class of Aaron Roth
    STOC 2024. Invited for submission to STOC 2024 special issue.
  • Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent. Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis. NeurIPS 2023. Link
  • Ambient Diffusion: Learning Clean Distributions from Corrupted Data. Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam R. Klivans. NeurIPS 2023. Link
  • Online Learning and Solving Infinite Games with an ERM Oracle. Angelos Assos, Idan Attias, Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson. COLT 2023. Link
  • Learning and Testing Latent-Tree Ising Models Efficiently. Davin Choo, Yuval Dagan, Constantinos Daskalakis, Anthimos Vardis Kandiros. COLT 2023. Link
  • EM’s Convergence in Gaussian Latent Tree Models. Yuval Dagan, Anthimos Vardis Kandiros, Constantinos Daskalakis. COLT 2022. Link
  • Smoothed online learning is as easy as statistical learning. Adam Block, Yuval Dagan, Noah Golowich, Alexander Rakhlin. COLT 2022. Link; Video (Block)
  • A bounded-noise mechanism for Differential privacy. Yuval Dagan and Gil Kur. COLT 2022. Link; Video
    (Resolves an open problem from differentialprivacy.org)
  • Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems.  Giannis Daras, Yuval Dagan, Alex Dimakis, Constantinos Daskalakis. ICML 2022. Link; Video (Daras)
  • Adversarial Laws of Large Numbers and Optimal Regret in Online Classification. Noga Alon, Omri Ben-Eliezer, Yuval Dagan, Shay Moran, Moni Naor, Eylon Yogev. STOC 2021 Link; Video
    Invited to STOC21 special issue
  • Learning Ising Models from One or Multiple Sample. Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Anthimos-Vardis Kandiros. STOC 2021 Link; Video 1 (Daskalakis, 66 min); Video 2 (Kandiros, 22 min)
  • Majorizing Measures, Sequential Complexities, and Online Learning. Adam Block, Yuval Dagan, Sasha Rakhlin. COLT 2021 Link; Video (Block)
  • Statistical Estimation from Dependent Data. Anthimos-Vardis Kandiros, Yuval Dagan, Nishanth Dikkala, Surbhi Goel, Constantinos Daskalakis. ICML 2021. Link; Video (Kandiros)
  • Yuval Dagan and Vitaly Feldman. Interaction is necessary for distributed learning with privacy or communication constraints. STOC 2020. Link; Video
    (Resolves a COLT 2019 open problem)
  • Yuval Dagan, Ohad Shamir. Detecting correlations with little memory and communication. Proceedings of the 31st Conference On Learning Theory, PMLR 75:1145-1198, 2018. Link; Video
  • Yuval Dagan, Yuval Filmus, Daniel Kane, Shay Moran. The entropy of lies: playing twenty questions with a liar. ITCS 2021. Link; Video
  • Yuval Dagan and Vitaly Feldman, PAC learning with stable and private predictions. COLT 2020 Link; Video
  • Yuval Dagan, Gil Kur, Ohad Shamir. Space lower bounds for linear prediction in the streaming model. Conference On Learning Theory 2019. Link; Video
  • Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Siddhartha Jayanti. Learning from weakly dependent data under Dobrushin’s condition. Conference on learning theory, 2019. Link; Video
  • Yuval Dagan and Gil Kur. The Log-Concave Maximum Likelihood Estimator is Optimal in High Dimensions. Link
  • Dagan, Y., Filmus, Y., Gabizon, A., & Moran, S. (2017, June). Twenty (simple) questions. In Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing (pp. 9-21). ACM. Link; Video
    Invited presentation in Highlights of Algorithms 2018
  • Dagan, Y., Filmus, Y., Hatami, H., & Li, Y. (2017, June). Trading information complexity for error. In 32nd Computational Complexity Conference (pp. 16:1-16:59). (CCC 2017 special issue)
    Link; Video (Hatami)
  • Yuval Dagan, Coby Crammer. A better resource allocation algorithm with semi bandit feedback. Algorithmic learning theory, 2018.
  • Yuval Dagan and Saar Zehavi. There is no online sparse regressor with sublinear regret. Project in the course “Advanced topics in Machine Learning” (Technion), fall 2015. (Resolves an open problem from COLT 2014)  Link

Teaching

(Spring 2025) Advanced topics in the connection between computational learning and game theories

Industry

  • Research internship at Google Brain, Summer 2019 (Host: Vitaly Feldman)
  • Facebook software engineering internship, Summer 2015 (Host: Rituraj Kirti)
  • Part-time student engineer at Mellanox Technologies, Architecture Department, 2013-14 (Host: Liran Liss)