paper-with-me

Papers

Generalization Analysis of Machine Learning Algorithms via the Worst-Case Data-Generating Probability Measure

2023-12-19 · Xinying Zou, Samir M. Perlaza, Iñaki Esnaola, Eitan Altman

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 measure and the unique solution to the maximization of the expected loss under a relative entropy constraint with respect to a reference probability measure. Fundamental generalization metrics, such as the sensitivity of the expected loss, the sensitivity of the empirical risk, and the generalization gap are shown to have closed-form expressions involving the worst-case data-generating probability measure. Existing results for the Gibbs algorithm, such as characterizing the generalization gap as a sum of mutual information and lautum information, up to a constant factor, are recovered. A novel parallel is established between the worst-case data-generating probability measure and the Gibbs algorithm. Specifically, the Gibbs probability measure is identified as a fundamental commonality of the model space and the data space for machine learning algorithms.

📄 PDF Abstract BibTeX arXiv:2312.12236

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Beyond the Worst-Case Analysis of Algorithms (Introduction)

2020-07-26 · Tim Roughgarden

One of the primary goals of the mathematical analysis of algorithms is to provide guidance about which algorithm is the "best" for solving a given computational problem. Worst-case analysis summarizes the performance pro…

The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

2022-04-09 · Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee 외

Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e.g., gene…

BIG-bench Machine LearningDomain Generalization

The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization

2022-01-01 · CVPR 2022 1 · Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee 외

Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e.g., …

BIG-bench Machine LearningDomain Generalization

Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds

2025-07-09 · Mario Tuci, Lennart Bastian, Benjamin Dupuis, Nassir Navab 외 arxiv

Providing generalization guarantees for stochastic optimization algorithms remains a key challenge in learning theory. Recently, numerous works demonstrated the impact of the geometric properties of optimization trajecto…

Stochastic Optimization

Learning-to-Optimize with PAC-Bayesian Guarantees: Theoretical Considerations and Practical Implementation

2024-04-04 · Michael Sucker, Jalal Fadili, Peter Ochs

We use the PAC-Bayesian theory for the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-Bayesian …