Avetik Karagulyan
- Centre National de la Recherche Scientifique (CNRS)
- Laboratoire des signaux et systèmes (L2S)
- CentraleSupélec
- Université Paris-Saclay
Publications
Publications
|
|
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisitedICLR International Conference on Learning Representations, 2024 |
|
|
Bounding the error of discretized Langevin algorithms for non-strongly log-concave targetsJournal of Machine Learning Research, 2022 |
|
|
Existence of positive solutions for an approximation of stationary mean-field gamesInvolve, a Journal of Mathematics, 2017, 10 (3), pp.473-493. ⟨10.2140/involve.2017.10.473⟩ |
|
|
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex OptimizationInternational Conference on Learning Representations, May 2024, Vienna, Austria |
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness ConditionThe 26th International Conference on Artificial Intelligence and Statistics, 2023, Valencia (Espagne), Spain. ⟨10.48550/arXiv.2206.00508⟩ |
|
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targetsNeural Information Processing Systems, Dec 2020, Vancouver (BC), Canada. pp.17594-17604, ⟨10.48550/arXiv.2006.13998⟩ |
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning2024 |
|
|
|
Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes2023 |
|
|
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression2023 |
|
|
Sampling with the Langevin Monte-CarloProbability [math.PR]. Institut Polytechnique de Paris, 2021. English. ⟨NNT : 2021IPPAG002⟩ |