Generalization analysis of machine learning algorithms via the worst-case data-generating probability measure
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 …
characterizing the generalization capabilities of machine learning algorithms. More …
Information-theoretic characterizations of generalization error for the Gibbs algorithm
Various approaches have been developed to upper bound the generalization error of a
supervised learning algorithm. However, existing bounds are often loose and even vacuous …
supervised learning algorithm. However, existing bounds are often loose and even vacuous …
Empirical risk minimization with relative entropy regularization: Optimality and sensitivity analysis
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 σ-finite …
regularization (ERM-RER) are investigated for the case in which the reference is a σ-finite …
The worst-case data-generating probability measure
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 …
characterizing the generalization capabilities of machine learning algorithms. More …
The worst-case data-generating probability measure in statistical learning
The worst-case data-generating (WCDG) probability measure is introduced as a tool for
characterizing the generalization capabilities of machine learning algorithms. Such a WCDG …
characterizing the generalization capabilities of machine learning algorithms. Such a WCDG …
Empirical risk minimization with f-divergence regularization in statistical learning
JFD Torres, I Esnaola, SM Perlaza, HV Poor - 2023 - hal.science
This report presents the solution to the empirical risk minimization with $ f $-divergence
regularization, under mild conditions on $ f $. Under such conditions, the optimal measure is …
regularization, under mild conditions on $ f $. Under such conditions, the optimal measure is …
Empirical risk minimization with relative entropy regularization type-II
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 …
with relative entropy regularization (ERM-RER) problem. A novel regularization is …
Modeling stationary, periodic, and long memory processes by superposed jump-driven processes
H Yoshioka - Chaos, Solitons & Fractals, 2024 - Elsevier
The long memory process is a stochastic process with power-type autocorrelation. Such
processes are found worldwide, and those arising in the environmental sciences often have …
processes are found worldwide, and those arising in the environmental sciences often have …
Equivalence of the Empirical Risk Minimization to Regularization on the Family of f-Divergences
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 …
DR) is presented under mild conditions on $ f $. Under such conditions, the optimal measure …
Generalization analysis of machine learning algorithms via the worst-case data-generating probability
X Zou, SM Perlaza, J Esnaola… - Proceedings of the …, 2023 - eprints.whiterose.ac.uk
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 …
characterizing the generalization capabilities of machine learning algorithms. More …