Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Aolin Xu"'
Publikováno v:
Shipin Kexue, Vol 45, Iss 17, Pp 277-286 (2024)
The sensory characteristics of foods have become an important part of measuring the quality of foods, and the descriptive analysis of sensory characteristics is of great significance to the evaluation of the sensory characteristics of foods. Currentl
Externí odkaz:
https://doaj.org/article/7b4e93a6f19a49dcabf1e4cbfb0da9e5
Autor:
Aolin Xu, Todd P. Coleman
Publikováno v:
ISIT
We consider the problem of estimating the unknown location of a spatial signal defined on a circular interval from noisy measurements. Lower bounds are derived for the minimax risk of the localization error defined by the circular distance. The lower
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::910cb33878b80171b8fb9584a9e83a66
https://doi.org/10.1109/isit44484.2020.9174122
https://doi.org/10.1109/isit44484.2020.9174122
Autor:
Aolin Xu
Publikováno v:
ISIT
We study the continuity property of the generalized entropy as a functional of probability distribution, defined with an action space and a loss function. Upper and lower bounds for the entropy difference of two distributions are derived in terms of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::add4ce06eda77b87b9dee72835b5f702
https://doi.org/10.1109/isit44484.2020.9174471
https://doi.org/10.1109/isit44484.2020.9174471
Autor:
Aolin Xu, Maxim Raginsky
We analyze the best achievable performance of Bayesian learning under generative models by defining and upper-bounding the minimum excess risk (MER): the gap between the minimum expected loss attainable by learning from data and the minimum expected
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0a0bc508ddc0f12062043ef1974e220
Autor:
Maxim Raginsky, Aolin Xu
Publikováno v:
IEEE Transactions on Information Theory. 63:1580-1600
We derive lower bounds on the Bayes risk in decentralized estimation, where the estimator does not have direct access to the random samples generated conditionally on the random parameter of interest, but only to the data received from local processo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::094cb41f34eba857787b2d5dca62d44d
https://doi.org/10.1109/tit.2016.2646342
https://doi.org/10.1109/tit.2016.2646342
Autor:
Naresh R. Shanbhag, Yingyan Lin, Min-Sun Keel, Andrew C. Singer, Aolin Xu, Elyse Rosenbaum, Adam C. Faust
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 63:693-704
Analog-to-digital converter (ADC)-based multi-Gb/s serial link receivers have gained increasing attention in the backplane community due to the desire for higher I/O throughput, ease of design portability, and flexibility. However, the power dissipat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f5966aa632143138f40d7aa4ad38ef03
https://doi.org/10.1109/tcsi.2016.2529284
https://doi.org/10.1109/tcsi.2016.2529284
Publikováno v:
ITW
Machine learning algorithms can be viewed as stochastic transformations that map training data to hypotheses. Following Bousquet and Elisseeff, we say that such an algorithm is stable if its output does not depend too much on any individual training
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3c688828b698063cd315ad4daadd9de2
https://doi.org/10.1109/itw.2016.7606789
https://doi.org/10.1109/itw.2016.7606789
Publikováno v:
IOP Conference Series: Earth and Environmental Science. 186:012026
Precise poverty alleviation is the strategic deployment of the new stage of the party and national anti-poverty development in the new period, and the poverty alleviation performance in poverty-stricken areas of Hainan province is related to the impo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c71a9d1487748883262175974358c33
https://doi.org/10.1088/1755-1315/186/6/012026
https://doi.org/10.1088/1755-1315/186/6/012026
Autor:
Aolin Xu, Maxim Raginsky
We derive information-theoretic converses (i.e., lower bounds) for the minimum time required by any algorithm for distributed function computation over a network of point-to-point channels with finite capacity, where each node of the network initiall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb906b563a8f2b8a4e005773cab15020
http://arxiv.org/abs/1509.00514
http://arxiv.org/abs/1509.00514