Title: The bounds of change-one generalization error under united algorithmic
Abstract: A notion of algorithmic stability under the changeone-error estimates,unitedstability,was introduced to study the generalization ability of machine learning under the condition of algorithmic stability.Using the extensions of Mc Diarmid's inquality,we obtain the bounds of machine learning generalization error under the condition of united stability.
Publication Year: 2005
Publication Date: 2005-01-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot