On calibration error of randomized forecasting algorithms

DOI10.1016/j.tcs.2009.01.010zbMath1167.68027OpenAlexW2097309800MaRDI QIDQ1017657

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

calibrationmachine learningrandomized roundingalgorithmic predictionrandomized predictionuniversal prediction

Mathematics Subject Classification ID

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

Related Items

DEGREES OF RANDOMIZED COMPUTABILITY, Randomization and entropy in machine learning and data processing, How to gamble against all odds, Failure of calibration is typical

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Algorithmic complexity bounds on future prediction errors
• Calibration-based empirical probability
• Non-stochastic infinite and finite sequences
• Probability and Finance
• Can an individual sequence of zeros and ones be random?
• Self-Calibrating Priors Do Not Exist
• The Well-Calibrated Bayesian
• Complexity-based induction systems: Comparisons and convergence theorems
• Asymptotic calibration
• Any Inspection is Manipulable
• Learning Theory
• Universal prediction
• Good Randomized Sequential Probability Forecasting is Always Possible
• THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS
• A formal theory of inductive inference. Part I
• Calibration with Many Checking Rules
• New error bounds for Solomonoff prediction