| User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient AS Dalalyan, AG Karagulyan Stochastic Processes and their Applications, 2017 | 352 | 2017 |
| Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets AS Dalalyan, A Karagulyan, L Riou-Durand Journal of Machine Learning Research 23 (235), 1-38, 2022 | 55 | 2022 |
| Convergence of Stein variational gradient descent under a weaker smoothness condition L Sun, A Karagulyan, P Richtarik International Conference on Artificial Intelligence and Statistics, 3693-3717, 2023 | 21 | 2023 |
| Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets A Karagulyan, AS Dalalyan Advances in Neural Information Processing Systems, 2020, 2020 | 13 | 2020 |
| Existence of positive solutions for an approximation of stationary mean-field games N Almayouf, E Bachini, A Chapouto, R Ferreira, D Gomes, D Jordăo, ... Involve, a Journal of Mathematics 10 (3), 473-493, 2016 | 10 | 2016 |
| Det-cgd: Compressed gradient descent with matrix stepsizes for non-convex optimization H Li, A Karagulyan, P Richtárik International Conference on Learning Representations 2024, 2024 | 5 | 2024 |
| ELF: Federated langevin algorithms with primal, dual and bidirectional compression A Karagulyan, P Richtárik arXiv preprint arXiv:2303.04622, 2023 | 5 | 2023 |
| SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning A Karagulyan, E Shulgin, A Sadiev, P Richtárik arXiv preprint arXiv:2405.20127, 2024 | 4 | 2024 |
| Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited L Yu, A Karagulyan, A Dalalyan International Conference on Learning Representations 2024, 2023 | 3 | 2023 |
| Sampling with the Langevin Monte-Carlo A Karagulyan Institut Polytechnique de Paris, 2021 | 2 | 2021 |
| Applying statistical learning theory to deep learning C Gerbelot, A Karagulyan, S Karp, K Ravichandran, M Stern, N Srebro Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104003, 2024 | 1 | 2024 |
| Variance reduced distributed non-convex optimization using matrix stepsizes H Li, A Karagulyan, P Richtárik arXiv, 2024 | 1 | 2024 |
| Non-asymptotic guarantees for sampling by stochastic gradient descent AG Karagulyan Journal of Contemporary Mathematical Analysis (Armenian Academy of Sciences …, 2019 | 1 | 2019 |
| MARINA Meets Matrix Stepsizes: Variance Reduced Distributed Non-convex Optimization H Li, A Karagulyan, P Richtárik arXiv preprint arXiv:2310.04614, 2023 | | 2023 |
Arnak S. DalalyanProfessor, CREST, ENSAE Paris, IP ParisEmail verificata su ensae.fr
