Zobrazeno 1 - 10
of 344
pro vyhledávání: '"Perlaza P"'
Autor:
Perlaza, Samir M., Zou, Xinying
In this paper, the method of gaps, a technique for deriving closed-form expressions in terms of information measures for the generalization error of machine learning algorithms is introduced. The method relies on two central observations: $(a)$~The g
Externí odkaz:
http://arxiv.org/abs/2411.12030
The effect of relative entropy asymmetry is analyzed in the context of empirical risk minimization (ERM) with relative entropy regularization (ERM-RER). Two regularizations are considered: $(a)$ the relative entropy of the measure to be optimized wit
Externí odkaz:
http://arxiv.org/abs/2410.02833
This paper characterizes the trade-offs between information and energy transmission over an additive white Gaussian noise channel in the finite block-length regime with finite channel input symbols. These trade-offs are characterized in the form of i
Externí odkaz:
http://arxiv.org/abs/2408.07807
This paper studies an instance of zero-sum games in which one player (the leader) commits to its opponent (the follower) to choose its actions by sampling a given probability measure (strategy). The actions of the leader are observed by the follower
Externí odkaz:
http://arxiv.org/abs/2402.02861
The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$. Under such conditions, the optimal measure is shown to be unique. Examples of the solution for particular choices of
Externí odkaz:
http://arxiv.org/abs/2402.00501
In this paper, the worst-case probability measure over the data is introduced as a tool for characterizing the generalization capabilities of machine learning algorithms. More specifically, the worst-case probability measure is a Gibbs probability me
Externí odkaz:
http://arxiv.org/abs/2312.12236
Autor:
Mahnaz Hosseinpour, Xinqi Xi, Ling Liu, Luis Malaver-Ortega, Laura Perlaza-Jimenez, Jihoon E. Joo, Harrison M. York, Jonathan Beesley, C. Elizabeth Caldon, Pierre-Antoine Dugué, James G. Dowty, Senthil Arumugam, Melissa C. Southey, Joseph Rosenbluh
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)
Abstract DNA methylation is an epigenetic mark that plays a critical role in regulating gene expression. DNA methyltransferase (DNMT) inhibitors, inhibit global DNA methylation and have been a key tool in studies of DNA methylation. A major bottlenec
Externí odkaz:
https://doaj.org/article/4b5c73d6eb4c45e2af8ef4e38c8d4099
Publikováno v:
IET Smart Grid, Vol 7, Iss 5, Pp 583-592 (2024)
Abstract A novel metric that describes the vulnerability of the measurements in power systems to data integrity attacks is proposed. The new metric, coined vulnerability index (VuIx), leverages information theoretic measures to assess the attack effe
Externí odkaz:
https://doaj.org/article/18f34d986e374d1791c451188ac74bfe
The dependence on training data of the Gibbs algorithm (GA) is analytically characterized. By adopting the expected empirical risk as the performance metric, the sensitivity of the GA is obtained in closed form. In this case, sensitivity is the perfo
Externí odkaz:
http://arxiv.org/abs/2306.12380
The effect of the relative entropy asymmetry is analyzed in the empirical risk minimization with relative entropy regularization (ERM-RER) problem. A novel regularization is introduced, coined Type-II regularization, that allows for solutions to the
Externí odkaz:
http://arxiv.org/abs/2306.07123