Profil personnel
Personal profile
Arnak Dalalyan is a full professor of Statistics at ENSAE Paris and the director of CREST. He obtained his PhD (2001) from Le Mans University on Statistics for Random Processes. He was a postdoctoral fellow (2002–03) at the Humboldt University of Berlin, an assistant professor (2003–08) at Paris 6 University and a research professor at ENPC (2008–2011). Arnak’s research focuses on high dimensional statistics, statistics of diffusion processes and statistical learning theory. Presently, he is an associate editor of the Annals of Statistics, Bernoulli, Statistical Inference for Stochastic Processes and Journal of the Japan Statistical Society. Arnak is also regularly serving in the programme committees (either as area chair or as reviewer) of machine learning conferences COLT, ALT, ICML and NeurIPS. He was a member of the Bernoulli Society council (2017-2021). Since 2014, Arnak Dalalyan is also the head of the ENSAE graduate programme on Statistics and Machine Learning.
Research Interests
High dimensional statistics
Compressed sensing
Nonparametric statistics
Machine learning
Learning theory
Qualification académique
HDR (PhD Supervision Credentials)
Empreinte digitale
- 1 Profils similaires
Collaborations et principaux domaines de recherche des cinq dernières années
Résultat de recherche
-
Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction
Bateni, A. H., Minasyan, A. & Dalalyan, A. S., 1 nov. 2025, Dans: Bernoulli. 31, 4, p. 2699-2722 24 p.Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
-
Parallelized midpoint randomization for Langevin Monte Carlo
Yu, L. & Dalalyan, A., 1 déc. 2025, Dans: Stochastic Processes and their Applications. 190, 104764.Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
Accès ouvert -
LANGEVIN MONTE CARLO FOR STRONGLY LOG-CONCAVE DISTRIBUTIONS: RANDOMIZED MID-POINT REVISITED
Yu, L., Karagulyan, A. & Dalalyan, A., 1 janv. 2024.Résultats de recherche: Contribution à une conférence › Papier › Revue par des pairs
-
Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Vardanyan, E., Hunanyan, S., Galstyan, T., Minasyan, A. & Dalalyan, A., 1 janv. 2024, Dans: Proceedings of Machine Learning Research. 235, p. 49203-49225 23 p.Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs
-
Matching Map Recovery with an Unknown Number of Outliers
Minasyan, A., Galstyan, T., Hunanyan, S. & Dalalyan, A., 1 janv. 2023, Dans: Proceedings of Machine Learning Research. 206, p. 891-906 16 p.Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs
-
Simple Proof of the Risk Bound for Denoising by Exponential Weights for Asymmetric Noise Distributions
Dalalyan, A. S., 1 déc. 2023, Dans: Journal of Contemporary Mathematical Analysis. 58, 6, p. 391-399 9 p.Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
-
ALL-IN-ONE ROBUST ESTIMATOR OF THE GAUSSIAN MEAN
DALALYAN, A. S. & Minasyan, A., 1 avr. 2022, Dans: Annals of Statistics. 50, 2, p. 1193-1219 27 p.Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
Accès ouvert -
Bounding the Error of Discretized Langevin Algorithms for Non-Strongly Log-Concave Targets
Dalalyan, A. S., Karagulyan, A. & Riou-Durand, L., 1 sept. 2022, Dans: Journal of Machine Learning Research. 23Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
-
Optimal detection of the feature matching map in presence of noise and outliers
Galstyan, T., Minasyan, A. & Dalalyan, A. S., 1 janv. 2022, Dans: Electronic Journal of Statistics. 16, 2, p. 5720-5750 31 p.Résultats de recherche: Contribution à un journal › Article › Revue par des pairs
Accès ouvert -
Risk bounds for aggregated shallow neural networks using Gaussian priors
Tinsi, L. & Dalalyan, A., 1 janv. 2022, Dans: Proceedings of Machine Learning Research. 178, p. 227-253 27 p.Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs