5 papers
Exact Permutation Recovery Under Unknown Scalar Affine Transformation
Tigran Galstyan, Avetik Karagulyan, Arshak Minasyan
We study the problem of matching two sets of noisy feature vectors when underlying true features are related by an unknown scalar affine transformation. Our method comprises two pr…
Improved Guarantees for Langevin Monte Carlo with Average Smoothness
Arnak S. Dalalyan, Avetik Karagulyan
We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein distance. The main result sho…
Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes
Hanmin Li, Avetik Karagulyan, Peter Richtárik
Matrix-stepsized gradient descent algorithms have been shown to have superior performance in non-convex optimization problems compared to their scalar counterparts. The det-CGD alg…
SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev +1
Cross-device training is a crucial subfield of federated learning, where the number of clients can reach into the billions. Standard approaches and local methods are prone to issue…
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
Hanmin Li, Avetik Karagulyan, Peter Richtárik
This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient Descent (CGD) algorithms enhanced with a matrix-v…