Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Stefano Rini"'
Publikováno v:
IEEE Transactions on Communications. 71:2654-2669
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4fe16571c8e00b374e3dd17ea67d5e4
https://doi.org/10.1109/tcomm.2023.3255251
https://doi.org/10.1109/tcomm.2023.3255251
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68dbe52d6da3cfc4c9e02450fd2ed4a0
https://doi.org/10.1109/icassp49357.2023.10097231
https://doi.org/10.1109/icassp49357.2023.10097231
Publikováno v:
2022 30th European Signal Processing Conference (EUSIPCO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ec4d5015fd81df7a64cf4bce2a05c55
https://doi.org/10.23919/eusipco55093.2022.9909717
https://doi.org/10.23919/eusipco55093.2022.9909717
Publikováno v:
2022 IEEE International Symposium on Information Theory (ISIT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3400b5482c3528c7c5be9265e8eae4b
https://doi.org/10.1109/isit50566.2022.9834470
https://doi.org/10.1109/isit50566.2022.9834470
Publikováno v:
IEEE Transactions on Information Theory. 67:2910-2924
Consider the problem of estimating a latent signal from a lossy compressed version of the data when the compressor is agnostic to the relation between the signal and the data. This situation arises in a host of modern applications when data is transm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1871002fe2a15e690a6fa500fc835d4
https://doi.org/10.1109/tit.2021.3068981
https://doi.org/10.1109/tit.2021.3068981
In this paper, we study the compression of a target two-layer neural network with N nodes into a compressed network with M < N nodes. More precisely, we consider the setting in which the weights of the target network are i.i.d. sub-Gaussian, and we m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f613a404d8e41f2fda8b529780392bbe
http://arxiv.org/abs/2205.08199
http://arxiv.org/abs/2205.08199
Autor:
Jamison R. Ebert, Vamsi K. Amalladinne, Stefano Rini, Jean-Francois Chamberland, Krishna R. Narayanan
Unsourced random access (URA) is a recently proposed multiple access paradigm tailored to the uplink channel of machine-type communication networks. By exploiting a strong connection between URA and compressed sensing, the massive multiple access pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::834a8103af5793f388b6af1705269e4d
http://arxiv.org/abs/2203.00239
http://arxiv.org/abs/2203.00239
In this paper, we study the problem of estimating the direction of arrival (DOA) using a sparsely sampled uniform linear array (ULA). Based on an initial incomplete ULA measurement, our strategy is to choose a sparse subset of array elements for meas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50b4341416315686d76b0264d7fc9b8b
http://arxiv.org/abs/2202.10148
http://arxiv.org/abs/2202.10148
Publikováno v:
ISIT 2022-IEEE International Symposium on Information Theory
ISIT 2022-IEEE International Symposium on Information Theory, Jun 2022, Espoo, Finland. pp.684-689, ⟨10.1109/ISIT50566.2022.9834273⟩
HAL
ISIT 2022-IEEE International Symposium on Information Theory, Jun 2022, Espoo, Finland. pp.684-689, ⟨10.1109/ISIT50566.2022.9834273⟩
HAL
The optimality and sensitivity of the empirical risk minimization problem with relative entropy regularization (ERM-RER) are investigated for the case in which the reference is a sigma-finite measure instead of a probability measure. This generalizat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3f8398b30ccb247d942f26918f37c914
http://arxiv.org/abs/2202.04385
http://arxiv.org/abs/2202.04385
In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in many distributed DNN training scenarios, including the recently popular federated learning (F
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d1c2d0ebbc584f5c80731c417617c05
http://arxiv.org/abs/2111.07599
http://arxiv.org/abs/2111.07599