Avetik Karagulyan
6 papers · 2020–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(5)
🏃
Academic Marathon
(5)
🐝
Cross-Pollinator
(9)
Conferences
ICLR (2)
AISTATS (1)
JMLR (1)
NIPS (1)
UAI (1)
Top co-authors
Keywords
wasserstein distance
(1)
variational inference
(1)
bayesian inference
(1)
kl divergence
(1)
markov chain monte carlo
(1)
probability distribution
(1)
convergence bound
(1)
langevin monte carlo
(1)
log-concave distribution
(1)
stein variational gradient descent
(1)
langevin algorithm
(1)
stein fisher information
(1)
sampling algorithm
(1)
langevin diffusion
(1)
stochastic diffusion
(1)
Papers
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression
UAI 2025
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
ICLR 2024
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
ICLR 2024
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition
AISTATS 2023
Bounding the Error of Discretized Langevin Algorithms for Non-Strongly Log-Concave Targets
JMLR 2022
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets
NIPS 2020