Zobrazeno 1 - 10
of 1 585
pro vyhledávání: '"Feofanov A"'
Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dime
Externí odkaz:
http://arxiv.org/abs/2409.12264
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
Autor:
Ilbert, Romain, Tiomoko, Malik, Louart, Cosme, Odonnat, Ambroise, Feofanov, Vasilii, Palpanas, Themis, Redko, Ievgen
In this paper, we introduce a novel theoretical framework for multi-task regression, applying random matrix theory to provide precise performance estimations, under high-dimensional, non-Gaussian data distributions. We formulate a multi-task optimiza
Externí odkaz:
http://arxiv.org/abs/2406.10327
Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the corresponding ground truth labels. Desp
Externí odkaz:
http://arxiv.org/abs/2405.18979
Autor:
Navakouski Maksim, Shilova Nadezhda, Khasbiullina Nailya, Feofanov Alexey, Pudova Elena, Chen Kowa, Blixt Ola, Bovin Nicolai
Publikováno v:
BioTechniques, Vol 64, Iss 3, Pp 110-116 (2018)
Despite considerable success studying glycan-binding proteins using printed glycan arrays (PGAs), unambiguous quantitation of spot intensities by fluorescent readers remains a challenge. The main obstacles are the varying spot shape and size and in-s
Externí odkaz:
https://doaj.org/article/45e1a996837e4ec0be6bf9c1faefce1e
Autor:
Ilbert, Romain, Odonnat, Ambroise, Feofanov, Vasilii, Virmaux, Aladin, Paolo, Giuseppe, Palpanas, Themis, Redko, Ievgen
Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this phenomenon, we
Externí odkaz:
http://arxiv.org/abs/2402.10198
Estimating test accuracy without access to the ground-truth test labels under varying test environments is a challenging, yet extremely important problem in the safe deployment of machine learning algorithms. Existing works rely on the information fr
Externí odkaz:
http://arxiv.org/abs/2401.08909
Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax prediction
Externí odkaz:
http://arxiv.org/abs/2310.14814
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10008-10033, 2023
We propose a theoretical framework to analyze semi-supervised classification under the low density separation assumption in a high-dimensional regime. In particular, we introduce QLDS, a linear classification model, where the low density separation a
Externí odkaz:
http://arxiv.org/abs/2310.13434
Autor:
Feofanov A.N., Busheva A.G.
Publikováno v:
MATEC Web of Conferences, Vol 346, p 03035 (2021)
This article discusses the main ways of selecting candidates for expert groups. The qualities necessary for an expert are indicated. Questionnaires have been developed, the answers to which will help to form a database of candidates. An algorithm is
Externí odkaz:
https://doaj.org/article/9b76190d3aee477cb124afff147a2dfe
Autor:
Feofanov Aleksandr
Publikováno v:
Vestnik Pravoslavnogo Svâto-Tihonovskogo Gumanitarnogo Universiteta: Seriâ II. Istoriâ, Istoriâ Russkoj Pravoslavnoj Cerkvi, Vol 4, Iss 71, Pp 53-57 (2016)
In the present article the number, social status and career achievements of pupils of the Noble Boarding School at the Moscow University is to be reconstructed on the basis of 1792 list. Despite the fact of the “noble” name of the Boarding School
Externí odkaz:
https://doaj.org/article/3c74ffb4e3a7403cb804a3085431b489