Hume's Problem Solved
The Optimality of Meta-Induction
A new approach to Hume's problem of induction that justifies the optimality of induction at the level of meta-induction.
Hume's problem of justifying induction has been among epistemology's greatest challenges for centuries. In this book, Gerhard Schurz proposes a new approach to Hume's problem. Acknowledging the force of Hume's arguments against the possibility of a noncircular justification of the reliability of induction, Schurz demonstrates instead the possibility of a noncircular justification of the optimality of induction, or, more precisely, of meta-induction (the application of induction to competing prediction models). Drawing on discoveries in computational learning theory, Schurz demonstrates that a regret-based learning strategy, attractivity-weighted meta-induction, is predictively optimal in all possible worlds among all prediction methods accessible to the epistemic agent. Moreover, the a priori justification of meta-induction generates a noncircular a posteriori justification of object induction. Taken together, these two results provide a noncircular solution to Hume's problem.
Schurz discusses the philosophical debate on the problem of induction, addressing all major attempts at a solution to Hume's problem and describing their shortcomings; presents a series of theorems, accompanied by a description of computer simulations illustrating the content of these theorems (with proofs presented in a mathematical appendix); and defends, refines, and applies core insights regarding the optimality of meta-induction, explaining applications in neighboring disciplines including forecasting sciences, cognitive science, social epistemology, and generalized evolution theory. Finally, Schurz generalizes the method of optimality-based justification to a new strategy of justification in epistemology, arguing that optimality justifications can avoid the problems of justificatory circularity and regress.
Hardcover$60.00 X | £50.00 ISBN: 9780262039727 400 pp. | 6 in x 9 in 38 b&w illus.
“Ever since Hume's skeptical arguments, the justification of induction has been in trouble. Gerhard Schurz presents a brave and brilliant solution by applying Reichenbach's comparative perspective first on the meta-level. A machine-learning-inspired kind of meta-induction can be shown a priori in a noncircular way to be predictively optimal among all accessible prediction methods. This enables the a posteriori comparative justification of object-induction. Schurz presents all this, and much more, in a transparent and convincing way.”
Professor Emeritus of Philosophy of Science, University of Groningen, the Netherlands
“Even if we cannot prove the reliability of induction, we still cannot do better than to rely on it. The case for this claim has never been made more forcefully and with greater insight and clarity than in this book. Drawing on cutting-edge research from machine learning, Gerhard Schurz provides readers with a wealth of new formal results, all geared toward showing the optimality of inductive reasoning. The book is engagingly written and, despite its formal nature, is also accessible to nonspecialists. The book should be read by anyone with an interest in epistemology or the philosophy of science, and indeed by all interested in the foundations of human knowledge.”
Centre National de la Recherche Scientifique (CNRS), Paris
“Can the problem of induction be solved? Following in the steps of Hans Reichenbach, and using modern logical and computational tools, Gerhard Schurz forcefully argues that the problem can be solved provided we focus our attention on the meta-level of competing prediction methods. He proves that his meta-inductive prediction strategy is optimal in the long run among all accessible prediction methods, and then shows that first-order induction should be trusted too. Along the way, Schurz examines all major philosophical stances concerning induction and proves a number of important theorems. Hume's Problem Solved is a tour de force of formal epistemology of science.”
University of Athens, Greece