Zobrazeno 1 - 10
of 19
pro vyhledávání: '"German Bassi"'
Publikováno v:
CNS
We consider a network of two nodes separated by a noisy channel, in which the source and its reconstruction have to be strongly coordinated, while simultaneously satisfying the strong secrecy condition with respect to an outside observer of the noisy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be478c379d5cf72d050cac1ada08a602
https://hal.archives-ouvertes.fr/hal-03114689
https://hal.archives-ouvertes.fr/hal-03114689
On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm
Publikováno v:
ITW
In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellstr\"om and Durisi [1]. First, we recover the bounds based on the individual sample mutual information from Bu et al. [2]
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a82099cda53a612090063627204bc7a
http://arxiv.org/abs/2010.10994
http://arxiv.org/abs/2010.10994
In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorithm is bounded from above by a function of the relative entropy between
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::edb64d4e2e133d67d4d6d15401bf9c1e
Publikováno v:
Privacy in Dynamical Systems ISBN: 9789811504921
We investigate the problem of sharing the outcomes of a parametric source with an untrusted party while ensuring the privacy of the parameters. We propose privacy mechanisms which guarantee parameter privacy under both Bayesian statistical as well as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6adaee5f0c5dff41e31fef91d312f3b
https://doi.org/10.1007/978-981-15-0493-8_4
https://doi.org/10.1007/978-981-15-0493-8_4
Autor:
German Bassi, Mikael Skoglund
Publikováno v:
ISIT
We investigate the behavior of the mutual information between two Boolean functions of correlated binary strings. The covariance of these functions is found to be a crucial parameter in the aforementioned mutual information. We then apply this result
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c3bce41db4f9c2439281f08064ccdeaf
https://doi.org/10.1109/isit.2019.8849315
https://doi.org/10.1109/isit.2019.8849315
Publikováno v:
ICASSP
Several recent works in communication systems have proposed to leverage the power of neural networks in the design of encoders and decoders. In this approach, these blocks can be tailored to maximize the transmission rate based on aggregated samples
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4656332be6ab4805611840151aba796
Publikováno v:
IEEE International Symposium on Information Theory (ISIT 2018)
IEEE International Symposium on Information Theory (ISIT 2018), Jun 2018, Vail, United States. ⟨10.1109/isit.2018.8437690⟩
ISIT
IEEE International Symposium on Information Theory (ISIT 2018), Jun 2018, Vail, United States. ⟨10.1109/isit.2018.8437690⟩
ISIT
International audience; We investigate the problem of sharing (communi-cating) the outcomes of a memoryless source when some of its statistical parameters must be kept private. Privacy is measured in terms of the Bayesian statistical risk according t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a869896802b2153962d0e3dc9dec91b2
https://hal-centralesupelec.archives-ouvertes.fr/hal-01756020
https://hal-centralesupelec.archives-ouvertes.fr/hal-01756020
Publikováno v:
ACC
There is a growing concern regarding the design of decentralized control systems. Witsenhausen's counterexample is a well-known problem which has remained open in this context, and emphasizes the necessity of communication between blocks in a distrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b7d2e759f1c9670504744bbbcdf8ba2
https://doi.org/10.23919/acc.2017.7963094
https://doi.org/10.23919/acc.2017.7963094
In this paper, we study a hypothesis test to determine the underlying directed graph structure of nodes in a network, where the nodes represent random processes and the direction of the links indicate a causal relationship between said processes. Spe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cad2ef4704ba913c7b6327aeb33b6dfc
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-226276
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-226276
Publikováno v:
2016 IEEE International Symposium on Information Theory (ISIT)
2016 IEEE International Symposium on Information Theory (ISIT), Jul 2016, Barcelona, Spain. ⟨10.1109/ISIT.2016.7541351⟩
2016 IEEE International Symposium on Information Theory (ISIT), Jul 2016, Barcelona, Spain. ⟨10.1109/ISIT.2016.7541351⟩
Information Theory, IEEE Transactions on (revised); This paper investigates the problem of secret key generation over a wiretap channel when the terminals observe correlated sources. These sources may or may not be independent of the main channel and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab6de9c6baeb25515ef95802bdea27f5
https://hal.archives-ouvertes.fr/hal-01436706
https://hal.archives-ouvertes.fr/hal-01436706