A Bayesian approach to (online) transfer learning: theory and algorithms

DOI10.1016/J.ARTINT.2023.103991arXiv2109.01377OpenAlexW4385728554MaRDI QIDQ6066772

Jingge Zhu, Uwe Aickelin, Xuetong Wu, Jonathan H. Manton

Publication date: 16 November 2023

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.01377

zbMATH Keywords

prior informationconditional mutual informationtransfer learningnegative transfer

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Bayesian problems; characterization of Bayes procedures (62C10) Information theory (general) (94A15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Online transfer learning
• Supervised sequence labelling with recurrent neural networks.
• Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems
• A theory of learning from different domains
• Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
• A Bayesian analysis of some nonparametric problems
• Information-theoretic asymptotics of Bayes methods
• Sample Selection Bias Correction Theory
• Information-theoretic upper and lower bounds for statistical estimation
• Universal prediction of individual sequences
• Asymptotic minimax regret for data compression, gambling, and prediction
• Sequential prediction of individual sequences under general loss functions
• Universal prediction
• Asymptotic normality of the posterior in relative entropy
• Universal portfolios with side information
• Fundamentals of Nonparametric Bayesian Inference

This page was built for publication: A Bayesian approach to (online) transfer learning: theory and algorithms