Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Ramon, Jan"'
Autor:
Korneev, Aleksei, Ramon, Jan
Federated Learning (FL) is a widespread approach that allows training machine learning (ML) models with data distributed across multiple devices. In cross-silo FL, which often appears in domains like healthcare or finance, the number of participants
Externí odkaz:
http://arxiv.org/abs/2410.09124
This work has two contributions. The first one is extending the Large Deviation Principle for uniform hyper-graphons from Lubetzky and Zhao \cite{lubetzky2015replica} to the multi-relational setting where each hyper-graphon can have different arities
Externí odkaz:
http://arxiv.org/abs/2403.09662
Autor:
Barczewski, Antoine, Ramon, Jan
Recently, due to the popularity of deep neural networks and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data privacy, there is a lot of interest in differentially private gradien
Externí odkaz:
http://arxiv.org/abs/2310.18001
Publikováno v:
Logical Methods in Computer Science, Volume 20, Issue 1 (January 26, 2024) lmcs:10232
In this paper, we study the problem of optimizing a linear program whose variables are the answers to a conjunctive query. For this we propose the language LP(CQ) for specifying linear programs whose constraints and objective functions depend on the
Externí odkaz:
http://arxiv.org/abs/2210.16694
Learning from data owned by several parties, as in federated learning, raises challenges regarding the privacy guarantees provided to participants and the correctness of the computation in the presence of malicious parties. We tackle these challenges
Externí odkaz:
http://arxiv.org/abs/2006.07218
A typical workflow for solving a linear programming problem is to first write a linear program parametrized by the data in a language such as Math GNU Prog or AMPL then call the solver on this program while providing the data. When the data is extrac
Externí odkaz:
http://arxiv.org/abs/1901.03633
The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as raises serious concerns for the privacy of individuals. In this paper,
Externí odkaz:
http://arxiv.org/abs/1803.09984
Autor:
Pelekis, Christos, Ramon, Jan
We provide a lower bound on the probability that a binomial random variable is exceeding its mean. Our proof employs estimates on the mean absolute deviation and the tail conditional expectation of binomial random variables.
Comment: 7 pages
Comment: 7 pages
Externí odkaz:
http://arxiv.org/abs/1604.06283
Let $Y_v, v\in V,$ be $[0,1]$-valued random variables having a dependency graph $G=(V,E)$. We show that \[ \mathbb{E}\left[\prod_{v\in V} Y_{v} \right] \leq \prod_{v\in V} \left\{ \mathbb{E}\left[Y_v^{\frac{\chi_b}{b}}\right] \right\}^{\frac{b}{\chi_
Externí odkaz:
http://arxiv.org/abs/1511.07204
Autor:
Pelekis, Christos, Ramon, Jan
We provide a systematic approach to deal with the following problem. Let $X_1,\ldots,X_n$ be, possibly dependent, $[0,1]$-valued random variables. What is a sharp upper bound on the probability that their sum is significantly larger than their mean?
Externí odkaz:
http://arxiv.org/abs/1507.06871