-
"MARINA Meets Matrix Stepsizes: Variance Reduced Distributed Non-Convex Optimization" -
Hanmin Li,
Avetik Karagulyan and
Peter Richtárik.
arXiv preprint arXiv:2310.04614, 2023
-
"Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited" -
Lu Yu,
Avetik Karagulyan and
Arnak Dalalyan,
International Conference on Learning Representations, 2024
-
"Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization" -
Hanmin Li,
Avetik Karagulyan and
Peter Richtárik.
International Conference on Learning Representations, 2024
-
"ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression" -
Avetik Karagulyan and
Peter Richtárik.
arXiv preprint arXiv:2303.04622, 2023
-
"Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition" -
Lukang Sun, Avetik Karagulyan and
Peter Richtárik.
International Conference on Artificial Intelligence and Statistics. PMLR, 2023.
-
"Sampling with the Langevin Monte-Carlo"
-
Avetik Karagulyan.
Supervised by Arnak Dalalyan
Thesis was defended at Institut Polytéchnique de Paris in June 2021.
-
"Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets"
- Avetik Karagulyan and Arnak S. Dalalyan.
Advances in Neural Information Processing Systems (NeurIPS 2020)
-
"Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets"
-
Arnak Dalalyan,
Lionel Riou-Durand and Avetik Karagulyan.
Journal of Machine Learning Research 23(235):1–38, 2022
-
"Non-Asymptotic Guarantees for Sampling by Stochastic Gradient Descent."
- Avetik Karagulyan.
Journal of Contemporary Mathematical Analysis (Armenian Academy of Sciences) 54.2 (2019): 71-78.
-
"User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient"
- Arnak S. Dalalyan and Avetik Karagulyan.
Stochastic Processes and their Applications 129.12 (2019): 5278-5311.