Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Pereverzyev, Sergei"'
Autor:
Gizewski, Elke R., Holzleitner, Markus, Mayer-Suess, Lukas, Pereverzyev Jr., Sergiy, Pereverzyev, Sergei V.
Most of the recent results in polynomial functional regression have been focused on an in-depth exploration of single-parameter regularization schemes. In contrast, in this study we go beyond that framework by introducing an algorithm for multiple pa
Externí odkaz:
http://arxiv.org/abs/2405.04147
Publikováno v:
Journal of Complexity, Volume 83, August 2024, 101853
This article offers a comprehensive treatment of polynomial functional regression, culminating in the establishment of a novel finite sample bound. This bound encompasses various aspects, including general smoothness conditions, capacity conditions,
Externí odkaz:
http://arxiv.org/abs/2311.03036
We discuss the problem of estimating Radon-Nikodym derivatives. This problem appears in various applications, such as covariate shift adaptation, likelihood-ratio testing, mutual information estimation, and conditional probability estimation. To addr
Externí odkaz:
http://arxiv.org/abs/2308.07887
Publikováno v:
Journal of Machine Learning Research 24 (395), 1-28, 2023
Estimating the ratio of two probability densities from finitely many observations of the densities is a central problem in machine learning and statistics with applications in two-sample testing, divergence estimation, generative modeling, covariate
Externí odkaz:
http://arxiv.org/abs/2307.16164
Sample reweighting is one of the most widely used methods for correcting the error of least squares learning algorithms in reproducing kernel Hilbert spaces (RKHS), that is caused by future data distributions that are different from the training data
Externí odkaz:
http://arxiv.org/abs/2307.11503
Autor:
Dinu, Marius-Constantin, Holzleitner, Markus, Beck, Maximilian, Nguyen, Hoan Duc, Huber, Andrea, Eghbal-zadeh, Hamid, Moser, Bernhard A., Pereverzyev, Sergei, Hochreiter, Sepp, Zellinger, Werner
Publikováno v:
International Conference On Learning Representations (ICLR), https://openreview.net/forum?id=M95oDwJXayG, 2023
We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to comp
Externí odkaz:
http://arxiv.org/abs/2305.01281
Publikováno v:
Numerical Functional Analysis and Optimization, 2024
The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we study domai
Externí odkaz:
http://arxiv.org/abs/2302.04724
Publikováno v:
In Journal of Complexity August 2024 83
Autor:
Maradesa, Adeleke, Py, Baptiste, Huang, Jake, Lu, Yang, Iurilli, Pietro, Mrozinski, Aleksander, Law, Ho Mei, Wang, Yuhao, Wang, Zilong, Li, Jingwei, Xu, Shengjun, Meyer, Quentin, Liu, Jiapeng, Brivio, Claudio, Gavrilyuk, Alexander, Kobayashi, Kiyoshi, Bertei, Antonio, Williams, Nicholas J., Zhao, Chuan, Danzer, Michael, Zic, Mark, Wu, Phillip, Yrjänä, Ville, Pereverzyev, Sergei, Chen, Yuhui, Weber, André, Kalinin, Sergei V., Schmidt, Jan Philipp, Tsur, Yoed, Boukamp, Bernard A., Zhang, Qiang, Gaberšček, Miran, O’Hayre, Ryan, Ciucci, Francesco
Publikováno v:
In Joule 17 July 2024 8(7):1958-1981
Autor:
Gizewski, Elke R., Mayer, Lukas, Moser, Bernhard A., Nguyen, Duc Hoan, Pereverzyev, Sergiy, Jr, Pereverzyev, Sergei V., Shepeleva, Natalia, Zellinger, Werner
Publikováno v:
In Applied and Computational Harmonic Analysis March 2022 57:201-227