Arnak Dalalyan
Affiliated Professor of Statistics and Data Science
Research Interests
Professor Dalalyan's teaching and research interests span mathematical statistics, learning theory, machine learning, and generative modeling. Email
In addition to his position at MBZUAI, Professor Dalalyan is a professor at the Statistics department of ENSAE Paris, Institut Polytechnique de Paris.
- Ph.D. in Applied Mathematics, Le Mans University, France
- Master's in Probability Theory, Pierre and Marie Curie University, France
- ERC advanced grant, 2025-2030
- Hi! PARIS Fellowship, 2021-2024
- Editor-in-Chief of Electronic Journal of Statistics, 2025-2028
- Director of CREST, 2020-2025
- Vahan Arsenyan, Antoine Grosnit, Haitham Bou Ammar, Arnak S. Dalalyan: "Contextual Causal Bayesian Optimisation", ICLR 2026.
- Amir-Hossein Bateni, Arshak Minasyan, Arnak S. Dalalyan: "Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction", Bernoulli, 31(4), pp. 2699-2722, 2025.
- Lu Yu, Arnak Dalalyan: "Parallelized midpoint randomization for Langevin Monte Carlo", Stochastic Processes and their Applications, 190, pp. 104764, 2025.
- Vahan Arsenyan, Elen Vardanyan, Arnak Dalalyan: "Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds", NeurIPS 2025.
- Lu Yu and Avetik G. Karagulyan, Arnak S. Dalalyan: "Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited:, ICLR 2024.
- Elen Vardanyan, Sona Hunanyan and Tigran Galstyan, Arshak Minasyan, Arnak S. Dalalyan: "Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution", ICML2024.