Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Pengqian Yu"'
Autor:
Haskell, William B., Pengqian, Yu
We are interested in solving convex optimization problems with large numbers of constraints. Randomized algorithms, such as random constraint sampling, have been very successful in giving nearly optimal solutions to such problems. In this paper, we c
Externí odkaz:
http://arxiv.org/abs/1610.06702
Autor:
Xinhan Di, Pengqian Yu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250651
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::169d3bb4b15808b1912b42c2cdb04fd7
https://doi.org/10.1007/978-3-031-25066-8_44
https://doi.org/10.1007/978-3-031-25066-8_44
Publikováno v:
IEEE Transactions on Automatic Control. 65:115-129
We propose universal randomized function approximation-based empirical value learning (EVL) algorithms for Markov decision processes. The “empirical” nature comes from each iteration being done empirically from samples available from simulations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::249b766b8f3321d61dfcfaa239e241d3
https://doi.org/10.1109/tac.2019.2907414
https://doi.org/10.1109/tac.2019.2907414
Publikováno v:
Federated Learning ISBN: 9783030968953
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e390b6b351532853562370f4be5e1219
https://doi.org/10.1007/978-3-030-96896-0_21
https://doi.org/10.1007/978-3-030-96896-0_21
Publikováno v:
Federated Learning ISBN: 9783030968953
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e7e499acefc5c879553955d6186bda5
https://doi.org/10.1007/978-3-030-96896-0_5
https://doi.org/10.1007/978-3-030-96896-0_5
Publikováno v:
Optimization. 68:2397-2426
The distributionally robust Markov Decision Process (MDP) approach asks for a distributionally robust strategy that achieves the maximal expected total reward under the most adversarial distributio...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e6fcb50c46b8d76d3d90315bce55434
https://doi.org/10.1080/02331934.2019.1655738
https://doi.org/10.1080/02331934.2019.1655738
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030668228
ECCV Workshops (4)
ECCV Workshops (4)
In this paper, we propose an assistive model that supports professional interior designers to produce industrial interior decoration solutions and to meet the personalized preferences of the property owners. The proposed model is able to automaticall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4d896a2cec746761c6b981b155dca7e
https://doi.org/10.1007/978-3-030-66823-5_27
https://doi.org/10.1007/978-3-030-66823-5_27
We present a class of methods for robust, personalized federated learning, called Fed+, that unifies many federated learning algorithms. The principal advantage of this class of methods is to better accommodate the real-world characteristics found in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8165f48247bacbb4912569973fa38f4d
Publikováno v:
International Journal of Computer Assisted Radiology and Surgery. 13:1439-1451
Flexible needle has the potential to accurately navigate to a treatment region in the least invasive manner. We propose a new planning method using Markov decision processes (MDPs) for flexible needle navigation that can perform robust path planning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3ca7ca13b64661edd716a0bacbdbc17
https://doi.org/10.1007/s11548-018-1783-x
https://doi.org/10.1007/s11548-018-1783-x
Publikováno v:
IJCNN
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between node
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43684ef65061548803da2e28223f843f
http://arxiv.org/abs/1905.08509
http://arxiv.org/abs/1905.08509