Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Sula, Erixhen"'
Autor:
Gastpar, Michael, Sula, Erixhen
The Shannon lower bound has been the subject of several important contributions by Berger. This paper surveys Shannon bounds on rate-distortion problems under mean-squared error distortion with a particular emphasis on Berger's techniques. Moreover,
Externí odkaz:
http://arxiv.org/abs/2409.14822
We study the problem of estimating the joint probability mass function (pmf) over two random variables. In particular, the estimation is based on the observation of $m$ samples containing both variables and $n$ samples missing one fixed variable. We
Externí odkaz:
http://arxiv.org/abs/2305.07955
Autor:
Sula, Erixhen, Zheng, Lizhong
The Expectation Maximization (EM) algorithm is widely used as an iterative modification to maximum likelihood estimation when the data is incomplete. We focus on a semi-supervised case to learn the model from labeled and unlabeled samples. Existing w
Externí odkaz:
http://arxiv.org/abs/2211.00537
Autor:
Sula, Erixhen, Gastpar, Michael
The Gray-Wyner network subject to a fidelity criterion is studied. Upper and lower bounds for the trade-offs between the private sum-rate and the common rate are obtained for arbitrary sources subject to mean-squared error distortion. The bounds meet
Externí odkaz:
http://arxiv.org/abs/2202.01260
Autor:
Sula, Erixhen, Gastpar, Michael
An important notion of common information between two random variables is due to Wyner. In this paper, we derive a lower bound on Wyner's common information for continuous random variables. The new bound improves on the only other general lower bound
Externí odkaz:
http://arxiv.org/abs/2102.08157
Autor:
Cho, Junho, Chandrasekhar, Sethumadhavan, Sula, Erixhen, Olsson, Samuel, Burrows, Ellsworth, Raybon, Greg, Ryf, Roland, Fontaine, Nicolas, Antona, Jean-Christophe, Grubb, Steve, Winzer, Peter, Chraplyvy, Andrew
We experimentally solve the problem of maximizing capacity under a total supply power constraint in a massively parallel submarine cable context, i.e., for a spatially uncoupled system in which fiber Kerr nonlinearity is not a dominant limitation. By
Externí odkaz:
http://arxiv.org/abs/2002.09297
Autor:
Gastpar, Michael, Sula, Erixhen
We give an information-theoretic interpretation of Canonical Correlation Analysis (CCA) via (relaxed) Wyner's common information. CCA permits to extract from two high-dimensional data sets low-dimensional descriptions (features) that capture the comm
Externí odkaz:
http://arxiv.org/abs/2002.00779
Autor:
Sula, Erixhen, Gastpar, Michael
We consider the problem of source coding subject to a fidelity criterion for the Gray-Wyner network that connects a single source with two receivers via a common channel and two private channels. The pareto-optimal trade-offs between the sum-rate of
Externí odkaz:
http://arxiv.org/abs/2002.01348
Autor:
Sula, Erixhen, Gastpar, Michael
Wyner's Common Information and a natural relaxation are studied in the special case of Gaussian random variables. The relaxation replaces conditional independence by a bound on the conditional mutual information. The main contribution is the proof th
Externí odkaz:
http://arxiv.org/abs/1912.07083
Autor:
Cho, Junho, Chandrasekhar, Sethumadhavan, Sula, Erixhen, Olsson, Samuel, Burrows, Ellsworth, Raybon, Greg, Ryf, Roland, Fontaine, Nicolas, Antona, Jean-Christophe, Grubb, Steve, Winzer, Peter, Chraplyvy, Andrew
We experimentally achieve a 19% capacity gain per Watt of electrical supply power in a 12-span link by eliminating gain flattening filters and optimizing launch powers using machine learning by deep neural networks in a massively parallel fiber conte
Externí odkaz:
http://arxiv.org/abs/1910.02050