Zobrazeno 1 - 10
of 141
pro vyhledávání: '"Perlaza, Samir M"'
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
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
The empirical risk minimization (ERM) problem with relative entropy regularization (ERM-RER) is investigated under the assumption that the reference measure is a $\sigma$-finite measure, and not necessarily a probability measure. Under this assumptio
Externí odkaz:
http://arxiv.org/abs/2211.06617
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 sets of channel input symbols. These trade-offs are characterized using im
Externí odkaz:
http://arxiv.org/abs/2211.05873