Karagulyan, Avetik

10 publications

UAI 2025 ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression Avetik Karagulyan, Peter Richtárik

ICLR 2024 Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization Hanmin Li, Avetik Karagulyan, Peter Richtárik

ICLR 2024 Langevin Monte Carlo for Strongly Log-Concave Distributions: Randomized Midpoint Revisited Lu Yu, Avetik Karagulyan, Arnak S. Dalalyan

NeurIPSW 2024 SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Nonconvex Cross-Device Federated Learning Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richtárik

AISTATS 2023 Convergence of Stein Variational Gradient Descent Under a Weaker Smoothness Condition Lukang Sun, Avetik Karagulyan, Peter Richtarik

NeurIPSW 2023 Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization Hanmin Li, Avetik Karagulyan, Peter Richtárik

ICMLW 2023 ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression Avetik Karagulyan, Peter Richtárik

NeurIPSW 2023 MARINA Meets Matrix Stepsizes: Variance Reduced Distributed Non-Convex Optimization Hanmin Li, Avetik Karagulyan, Peter Richtárik

JMLR 2022 Bounding the Error of Discretized Langevin Algorithms for Non-Strongly Log-Concave Targets Arnak S. Dalalyan, Avetik Karagulyan, Lionel Riou-Durand

NeurIPS 2020 Penalized Langevin Dynamics with Vanishing Penalty for Smooth and Log-Concave Targets Avetik Karagulyan, Arnak Dalalyan