On calibration error of randomized forecasting algorithms

DOI10.1016/J.TCS.2009.01.010MaRDI QIDQ1017657zbMATH OpenOpenAlexFDO

Authors Vladimir V. V'yugin

Publication date 12 May 2009

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2009.01.010

zbMATH Keywords

machine learningcalibrationalgorithmic predictionrandomized roundingrandomized predictionuniversal prediction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Inference from stochastic processes and prediction (62M20) Computational learning theory (68Q32) Randomized algorithms (68W20)

Recommendations

• On Calibration Error of Randomized Forecasting Algorithms
• Asymptotic calibration
• On Sequences with Non-learnable Subsequences
• Good Randomized Sequential Probability Forecasting is Always Possible
• Non-asymptotic calibration and resolution

Cites work

• scientific article; zbMATH DE number 1010621 (Why is no real title available?)
• scientific article; zbMATH DE number 3802533 (Why is no real title available?)
• scientific article; zbMATH DE number 3291134 (Why is no real title available?)
• A formal theory of inductive inference. Part I
• Algorithmic complexity bounds on future prediction errors
• Any Inspection is Manipulable
• Asymptotic calibration
• Calibration with Many Checking Rules
• Calibration-based empirical probability
• Can an individual sequence of zeros and ones be random?
• Complexity-based induction systems: Comparisons and convergence theorems
• Good Randomized Sequential Probability Forecasting is Always Possible
• Learning Theory
• New error bounds for Solomonoff prediction
• Non-stochastic infinite and finite sequences
• Probability and finance. It's only a game!
• Self-Calibrating Priors Do Not Exist
• THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS
• The Well-Calibrated Bayesian
• Universal prediction

Cited in

(11)

• How to gamble against all odds
• Randomization and entropy in machine learning and data processing
• Algorithmic Learning Theory
• Sampling Distributions of Post-Sample Forecasting Errors
• Probabilistic Forecasts, Calibration and Sharpness
• On Calibration Error of Randomized Forecasting Algorithms
• Failure of calibration is typical
• Non-asymptotic calibration and resolution
• Good Randomized Sequential Probability Forecasting is Always Possible
• Costly miscalibration
• Degrees of randomized computability

This page was built for publication: On calibration error of randomized forecasting algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1017657)