Karagulyan, Avetik and Arnak S. Dalalyan. "Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets"

Advances in Neural Information Processing Systems (NeurIPS 2020)


Dalalyan, Arnak S., Lionel Riou-Durand and Avetik Karagulyan. "Bounding the error of discretized Langevin algorithms for non-strongly log-concave targets" arXiv preprint arXiv:1906.08530 (2019)


Karagulyan, Avetik "Non-Asymptotic Guarantees for Sampling by Stochastic Gradient Descent."

Journal of Contemporary Mathematical Analysis (Armenian Academy of Sciences) 54.2 (2019): 71-78.


Dalalyan, Arnak S. and Avetik Karagulyan. "User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient."

Stochastic Processes and their Applications 129.12 (2019): 5278-5311.