Skip to content

Algorithmic learning in a random world

Algorithmic learning in a random world

MathematicsScience
Pages
340
Published
2005
Language
English

Synopsis

This monograph introduces conformal prediction, a powerful machine learning method that offers both high accuracy and reliable information about its own precision. It mathematically validates the reliability of conformal predictors for independent and identically distributed data, while experimentally confirming their practical accuracy. The book extends these findings to repetitive structures, integrating various machine learning techniques from boosting to nearest neighbors, and explores connections to algorithmic randomness and statistical physics.

Prose complexity
10/10

Vibe

InformativeIntellectualComplex

Genres

Mathematics Science Technology

Authors

G
Glenn Shafer

Glenn Shafer is a key figure in probability and decision theory. His books, including Readings in uncertain reasoning and Game-Theoretic Foundations for Probability and Finance, explore how we understand and model uncertainty. He also writes on algorithmic learning and its role in a random world.

V
Vladimir Vovk

Vladimir Vovk is a distinguished author specializing in statistical learning, probability, and algorithmic complexity. His notable works include Measures of Complexity, Statistical Learning and Data Sciences, and Algorithmic Learning in a Random World. Vovk also explores game theory in Game-Theoretic Foundations for Probability and Finance.