Optimal sampling of parametric families: implications for machine learning

DOI10.1162/NECO_A_01251MaRDI QIDQ5131174zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Adrian E. G. Huber, Jithendar Anumula, Shihchii Liu

Publication date 2 November 2020

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://www.zora.uzh.ch/id/eprint/184150/1/document09.56.pdf

Mathematics Subject Classification ID

Diffusion processes (60J60) Sequential estimation (62L12) Inference from stochastic processes and prediction (62M20) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning models with uniform performance via distributionally robust optimization
• On robust sequential parameters estimating
• Mismatched training and test distributions can outperform matched ones
• Adaptive sequential machine learning
• Machine learning from a continuous viewpoint. I

Cites work

• A strong version of the redundancy-capacity theorem of universal coding
• Fisher information and stochastic complexity
• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1150732 (Why is no real title available?)
• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• Information and complexity in statistical modeling.
• Nonparametric risk bounds for time-series forecasting
• Predictors for the first-order autoregressive process
• Properties of Predictors for Autoregressive Time Series
• The strong ergodic theorem for densities: Generalized Shannon-McMillan- Breiman theorem
• Theory of statistical inference and information. Transl. from the Slovak by the author
• Universal coding, information, prediction, and estimation
• Universal prediction

Cited in

(2)

• Mismatched training and test distributions can outperform matched ones
• Robust data sampling in machine learning: a game-theoretic framework for training and validation data selection

This page was built for publication: Optimal sampling of parametric families: implications for machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5131174)