Zobrazeno 1 - 10
of 1 843
pro vyhledávání: '"Shulgin A"'
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 issues such as client drift and insensitivity to data similarities. We prop
Externí odkaz:
http://arxiv.org/abs/2405.20127
Autor:
Rustam A. Shakhaliev, Andrey S. Shulgin, Nikita D. Kubin, Anton S. Kondratiev, Denis A. Suchkov, Sofia V. Neklasova, Dmitry D. Shkarupa
Publikováno v:
Trials, Vol 25, Iss 1, Pp 1-11 (2024)
Abstract Background Pelvic organ prolapse (POP) is one of the most common pathologies of the pelvic floor, and it can be found among 40–60% of women who have given birth. Correction of the defect of the DeLancey level II without reconstruction of t
Externí odkaz:
https://doaj.org/article/da44e6c5eaa34c68be3efe28d9c29978
Publikováno v:
MATEC Web of Conferences, Vol 329, p 03010 (2020)
The analysis of causes of destruction of main gas pipelines for the last two decades is carried out. It is shown that the share of accidents because of corrosion cracking energized increases. The conclusion is drawn that inspection and repair of emer
Externí odkaz:
https://doaj.org/article/88d5c277ec384847a20fe5b5b54ddfac
Autor:
Shulgin, Egor, Richtárik, Peter
Modern advancements in large-scale machine learning would be impossible without the paradigm of data-parallel distributed computing. Since distributed computing with large-scale models imparts excessive pressure on communication channels, significant
Externí odkaz:
http://arxiv.org/abs/2306.16484
Autor:
Nataliya Kudryashova, Boris Shulgin, Nikolai Katuninks, Victoria Kulesh, Gabriel Helmlinger, Kirill Zhudenkov, Kirill Peskov
Publikováno v:
Computational and Structural Biotechnology Journal, Vol 24, Iss , Pp 611-621 (2024)
We present a meta-analytics approach to quantify NSCLC disease burden by integrative survival models. Aggregated survival data from public sources were used to parameterize the models for early as well as advanced NSCLC stages incorporating chemother
Externí odkaz:
https://doaj.org/article/f1bddf6d7f444c1cb4812e815104bec8
Autor:
S. Shulgin
Publikováno v:
Аналітично-порівняльне правознавство, Iss 5 (2024)
У статті проведено дослідження правових наслідків проголошення стороною захисту заяви про провокацію злочину. На підставі аналізу пр
Externí odkaz:
https://doaj.org/article/01314138a24f473f9ec9093e14ac5a54
Autor:
Shakhaliev, Rustam A.1 (AUTHOR) rustam.shahaliev@gmail.com, Shulgin, Andrey S.1 (AUTHOR), Kubin, Nikita D.1 (AUTHOR), Kondratiev, Anton S.1 (AUTHOR), Suchkov, Denis A.1 (AUTHOR), Neklasova, Sofia V.1 (AUTHOR), Shkarupa, Dmitry D.1 (AUTHOR)
Publikováno v:
Trials. 10/2/2024, Vol. 25 Issue 1, p1-11. 11p.
Autor:
Valeriy Borisovich Gostenin, Anton Mikhailovich Shulgin, Irina Sergeevna Shikhovtseva, Alexandra Alexandrovna Kalinina, Inessa Alexandrovna Gritskova, Vitaliy Pavlovich Zubov
Publikováno v:
Physchem, Vol 4, Iss 1, Pp 78-90 (2024)
The effects of the molecular architecture of water-insoluble organosilicon polymerizable surfactant macromers (SAMs) on their colloidal-chemical characteristics and on their efficiency in heterophase radical polymerization of styrene and methyl metha
Externí odkaz:
https://doaj.org/article/f58fa013c8d445b0912e0d14347a64e9
Autor:
Shulgin, Egor, Richtárik, Peter
Communication is one of the key bottlenecks in the distributed training of large-scale machine learning models, and lossy compression of exchanged information, such as stochastic gradients or models, is one of the most effective instruments to allevi
Externí odkaz:
http://arxiv.org/abs/2206.10452
Federated learning has recently gained significant attention and popularity due to its effectiveness in training machine learning models on distributed data privately. However, as in the single-node supervised learning setup, models trained in federa
Externí odkaz:
http://arxiv.org/abs/2206.02535