Zobrazeno 1 - 10
of 112
pro vyhledávání: '"Kuznetsov, Vitaly"'
Autor:
Kuznetsov, Vitaly V.1 (AUTHOR), Poineau, Frederic2 (AUTHOR) poineauf@unlv.nevada.edu, German, Konstantin E.1 (AUTHOR), Filatova, Elena A.3 (AUTHOR)
Publikováno v:
Communications Chemistry. 11/11/2024, Vol. 7 Issue 1, p1-13. 13p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Weill, Charles, Gonzalvo, Javier, Kuznetsov, Vitaly, Yang, Scott, Yak, Scott, Mazzawi, Hanna, Hotaj, Eugen, Jerfel, Ghassen, Macko, Vladimir, Adlam, Ben, Mohri, Mehryar, Cortes, Corinna
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns the struc
Externí odkaz:
http://arxiv.org/abs/1905.00080
Autor:
Kuznetsov, Vitaly, Mariet, Zelda
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecastin
Externí odkaz:
http://arxiv.org/abs/1805.03714
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We present new online algorithms for path learning with non-additive count-b
Externí odkaz:
http://arxiv.org/abs/1804.06518
Autor:
Kuznetsov, Vitaly, Mohri, Mehryar
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that c
Externí odkaz:
http://arxiv.org/abs/1803.05814
We study the multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes, a setting that generalizes many existing lines of work and analyses. In particular, we present a theoretical analysis and deriv
Externí odkaz:
http://arxiv.org/abs/1710.10657
Autor:
Kurdin, Kirill A. *, Kuznetsov, Vitaly V., Sinitsyn, Vitaly V., Galitskaya, Elena A., Filatova, Elena A., Belina, Charles A., Stevenson, Keith J.
Publikováno v:
In Catalysis Today 1 April 2022 388-389:147-157
We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including data-dependent general
Externí odkaz:
http://arxiv.org/abs/1607.01097
We present a general theoretical analysis of structured prediction with a series of new results. We give new data-dependent margin guarantees for structured prediction for a very wide family of loss functions and a general family of hypotheses, with
Externí odkaz:
http://arxiv.org/abs/1605.06443