Entrar
insight - Generalization Bounds
Generalization Bounds: Information-Theoretic and PAC-Bayes Perspectives
Information-theoretic and PAC-Bayesian perspectives provide insights into generalization bounds in machine learning.
Generalization Bounds for Learning Algorithms Trained on Data with Graph-Based Dependencies
This paper introduces a novel framework for deriving generalization bounds for learning algorithms trained on data with dependencies encoded by a graph structure, where the strength of dependencies decays with graph distance.
Online-to-PAC Conversions: Using Online Learning's Regret Analysis to Establish Generalization Bounds for Statistical Learning Algorithms
This paper introduces a novel framework called "online-to-PAC conversion" that leverages online learning techniques, specifically regret analysis, to derive generalization bounds for statistical learning algorithms.