Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Alexandre Proutiere"'
Publikováno v:
Quantitative Finance. :1-28
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eba70decb532feaa311f3ee9e2523873
https://doi.org/10.1080/14697688.2023.2205583
https://doi.org/10.1080/14697688.2023.2205583
Autor:
Yassir Jedra, Alexandre Proutiere
Publikováno v:
IEEE Transactions on Automatic Control. 68:2805-2820
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40d490679fd2da065ef3a8fcf0135625
https://doi.org/10.1109/tac.2022.3221705
https://doi.org/10.1109/tac.2022.3221705
Publikováno v:
IEEE Transactions on Vehicular Technology. 72:546-556
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64de6e963226ceb86c1148793b3e7991
https://doi.org/10.1109/tvt.2022.3202041
https://doi.org/10.1109/tvt.2022.3202041
Publikováno v:
IEEE Transactions on Automatic Control. :1-16
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8f219168fd1501c1cbdbc2ef49193ef5
https://doi.org/10.1109/tac.2023.3241237
https://doi.org/10.1109/tac.2023.3241237
Publikováno v:
IEEE Transactions on Information Theory. 67:616-639
We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the network-wide data. It then updates its predi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de60f45d4cce3eb2164789afd3e00ba5
https://doi.org/10.1109/tit.2020.3029304
https://doi.org/10.1109/tit.2020.3029304
Publikováno v:
Ann. Statist. 48, no. 6 (2020), 3488-3512
The Annals of Statistics, 48(6), 3488-3512. Institute of Mathematical Statistics
The Annals of Statistics, 48(6), 3488-3512. Institute of Mathematical Statistics
This paper considers cluster detection in Block Markov Chains (BMCs). These Markov chains are characterized by a block structure in their transition matrix. More precisely, the $n$ possible states are divided into a finite number of $K$ groups or clu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e93b8cb0eef7ad6c15bd0f3717c7d55
http://www.scopus.com/inward/record.url?scp=85099016536&partnerID=8YFLogxK
http://www.scopus.com/inward/record.url?scp=85099016536&partnerID=8YFLogxK
Publikováno v:
IEEE Transactions on Mobile Computing. 18:1145-1158
Rate Adaptation (RA) is a fundamental mechanism in 802.11 systems. It allows transmitters to adapt the coding and modulation scheme as well as the MIMO transmission mode to the radio channel conditions, to learn and track the (mode, rate) pair provid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd8006703b7253bea4e2b8c70a446587
https://doi.org/10.1109/tmc.2018.2854758
https://doi.org/10.1109/tmc.2018.2854758
Autor:
Alessio Russo, Alexandre Proutiere
Publikováno v:
ACC
Control policies, trained using Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even minimal perturbations to the policy input. The attacks proposed so far have been designed using heuristics,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1832cdf90214a03147253563373e3fd
https://doi.org/10.23919/acc50511.2021.9483025
https://doi.org/10.23919/acc50511.2021.9483025
Autor:
Alessio Russo, Alexandre Proutiere
Publikováno v:
ACC
This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastically deteriorate the prediction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34ea223ff9709aedf957800648566956
http://arxiv.org/abs/2103.06199
http://arxiv.org/abs/2103.06199
Publikováno v:
MED
This work investigates the feasibility of using input-output data-driven control techniques for building control and their susceptibility to data-poisoning techniques. The analysis is performed on a digital replica of the KTH Live- in Lab, a non-line
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba9015bd054ef0265c05df7b0ce227d7
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-304670
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-304670