\( \lambda \)-deformed evidence lower bound (\( \lambda \)-ELBO) using Rényi and Tsallis divergence

DOI10.1007/978-3-031-38271-0_19OpenAlexW4385435142MaRDI QIDQ6178840

No author found.

Publication date: 16 January 2024

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-031-38271-0_19

zbMATH Keywords

variational autoencoderevidence lower bound\( \lambda \)-deformation

Mathematics Subject Classification ID

Robustness and adaptive procedures (parametric inference) (62F35) Measures of information, entropy (94A17) Statistical aspects of information-theoretic topics (62B10)

Cites Work

• Unnamed Item
• Families of alpha-, beta- and gamma-divergences: flexible and robust measures of similarities
• Robust parameter estimation with a small bias against heavy contamination
• Robust extraction of local structures by the minimum \(\beta\)-divergence method
• Robust Blind Source Separation by Beta Divergence
• Robust and efficient estimation by minimising a density power divergence
• Bayesian Brains and the Rényi Divergence
• Tsallis and Rényi Deformations Linked via a New λ-Duality
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations

This page was built for publication: \( \lambda \)-deformed evidence lower bound (\( \lambda \)-ELBO) using Rényi and Tsallis divergence