Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers

no code implementations • 24 May 2024 • Vladislav Trifonov, Alexander Rudikov, Oleg Iliev, Ivan Oseledets, Ekaterina Muravleva

In our work, we recall well-established preconditioners from linear algebra and use them as a starting point for training the GNN.

Quantization of Large Language Models with an Overdetermined Basis

no code implementations • 15 Apr 2024 • Daniil Merkulov, Daria Cherniuk, Alexander Rudikov, Ivan Oseledets, Ekaterina Muravleva, Aleksandr Mikhalev, Boris Kashin

In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation.

Data Compression Quantization +2

Reconstruction of 3D Porous Media From 2D Slices

no code implementations • 29 Jan 2019 • Denis Volkhonskiy, Ekaterina Muravleva, Oleg Sudakov, Denis Orlov, Boris Belozerov, Evgeny Burnaev, Dmitry Koroteev

In many branches of earth sciences, the problem of rock study on the micro-level arises.

Data-driven model for the identification of the rock type at a drilling bit

no code implementations • 8 Jun 2018 • Nikita Klyuchnikov, Alexey Zaytsev, Arseniy Gruzdev, Georgiy Ovchinnikov, Ksenia Antipova, Leyla Ismailova, Ekaterina Muravleva, Evgeny Burnaev, Artyom Semenikhin, Alexey Cherepanov, Vitaliy Koryabkin, Igor Simon, Alexey Tsurgan, Fedor Krasnov, Dmitry Koroteev

Directional oil well drilling requires high precision of the wellbore positioning inside the productive area.

BIG-bench Machine Learning General Classification