no code implementations • 11 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.
no code implementations • 10 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.
1 code implementation • 27 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.
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.
no code implementations • 6 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