On calibration error of randomized forecasting algorithms

DOI10.1016/J.TCS.2009.01.010zbMATH Open1167.68027OpenAlexW2097309800MaRDI QIDQ1017657FDOQ1017657

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

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

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)

Cites Work

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

Cited In (11)

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

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)