Zobrazeno 1 - 10
of 13 722
pro vyhledávání: '"Empirical Risk Minimization"'
We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p \geq 1$. We propose a black-box reduction method that, by employing properties of unifor
Externí odkaz:
http://arxiv.org/abs/2412.15956
Autor:
Han, Qiyang, Xu, Xiaocong
Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has therefore limited its broader pote
Externí odkaz:
http://arxiv.org/abs/2412.09498
Autor:
Hanneke, Steve, Xu, Mingyue
The well-known empirical risk minimization (ERM) principle is the basis of many widely used machine learning algorithms, and plays an essential role in the classical PAC theory. A common description of a learning algorithm's performance is its so-cal
Externí odkaz:
http://arxiv.org/abs/2412.02810
This paper establishes bounds on the predictive performance of empirical risk minimization for principal component regression. Our analysis is nonparametric, in the sense that the relation between the prediction target and the predictors is not speci
Externí odkaz:
http://arxiv.org/abs/2409.03606
Autor:
Pfau, Diana, Jung, Alexander
AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases, opacity,
Externí odkaz:
http://arxiv.org/abs/2410.19361
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
Autor:
Milz, Johannes, Walter, Daniel
Nonsmooth composite optimization problems under uncertainty are prevalent in various scientific and engineering applications. We consider risk-neutral composite optimal control problems, where the objective function is the sum of a potentially noncon
Externí odkaz:
http://arxiv.org/abs/2408.10384
Publikováno v:
In Expert Systems With Applications 1 February 2025 261
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
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