Search Results for author: Yury Demidovich

Found 5 papers, 1 papers with code

Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction

no code implementations11 Mar 2024 Yury Demidovich, Grigory Malinovsky, Peter Richtárik

These methods replace the outer loop with probabilistic gradient computation triggered by a coin flip in each iteration, ensuring simpler proofs, efficient hyperparameter selection, and sharp convergence guarantees.

Distributed Optimization Riemannian optimization

Correlated Quantization for Faster Nonconvex Distributed Optimization

no code implementations10 Jan 2024 Andrei Panferov, Yury Demidovich, Ahmad Rammal, Peter Richtárik

We analyze the forefront distributed non-convex optimization algorithm MARINA (Gorbunov et al., 2022) utilizing the proposed correlated quantizers and show that it outperforms the original MARINA and distributed SGD of Suresh et al. (2022) with regard to the communication complexity.

Distributed Optimization Quantization

MAST: Model-Agnostic Sparsified Training

1 code implementation27 Nov 2023 Yury Demidovich, Grigory Malinovsky, Egor Shulgin, Peter Richtárik

We introduce a novel optimization problem formulation that departs from the conventional way of minimizing machine learning model loss as a black-box function.

Graph-based Nearest Neighbor Search in Hyperbolic Spaces

no code implementations ICLR 2022 Liudmila Prokhorenkova, Dmitry Baranchuk, Nikolay Bogachev, Yury Demidovich, Alexander Kolpakov

From a theoretical perspective, we rigorously analyze the time and space complexity of graph-based NNS, assuming that an n-element dataset is uniformly distributed within a d-dimensional ball of radius R in the hyperbolic space of curvature -1.

Information Retrieval Retrieval +1

Tight asymptotics of clique-chromatic numbers of dense random graphs

no code implementations6 Dec 2020 Yury Demidovich, Maksim Zhukovskii

The clique chromatic number of a graph is the minimum number of colors required to assign to its vertex set so that no inclusion maximal clique is monochromatic.

Combinatorics 05C80, 05C15

Cannot find the paper you are looking for? You can Submit a new open access paper.