No Free Lunch Theorem, Inductive Skepticism, and the Optimality of Meta-induction
Bibliographic Data
| ID | 10706300 |
|---|---|
| Authors | Gerhard Schurz (0000-0002-4107-9240, corresponding author) |
| Year | 2017 |
| Volume | 84 |
| Issue | 5 |
| Pages | 825-839 |
| Publication date | 2017-12-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Philosophy of Science (JOURNAL) |
| Journal identifiers | ISSN: 0031-8248 • E-ISSN: 1539-767X |
| Publisher | Cambridge University Press (CUP) (PUBLISHER) |
| DOI | 10.1086/693929 |
| OpenAlex | W2548389436 |
| Language | EN |
| Citations received | 7 |
| References cited | 4 |
The no free lunch theorem is a radicalized version of Hume’s induction skepticism. It asserts that relative to a uniform probability distribution over all possible worlds, all computable prediction algorithms—whether ‘clever’ inductive or ‘stupid’ guessing methods (etc.)—have the same expected predictive success. This theorem seems to be in conflict with results about meta-induction. According to these results, certain meta-inductive prediction strategies may dominate other (non-meta-inductive) methods in their predictive success (in the long run). In this article this conflict is analyzed and dissolved, by means of probabilistic analysis and computer simulation
Discrete mathematics · Economics · Epistemology · Inductive bias · Inductive method · Inductive reasoning · Mathematical economics · Mathematics education · Meta-analysis · Probabilistic logic · Skepticism · Advanced Bandit Algorithms Research · Adversarial Robustness in Machine Learning · Artificial Intelligence · Computability, Logic, AI Algorithms · Computer Science · Mathematics · Medicine · Philosophy
Does Meta-induction Justify Induction
Non-epistemic Values and the Automation of Science
Explaining the Success of Induction
Metainduction over Unboundedly Many Prediction Methods
The no-free-lunch theorems of supervised learning
No free theory choice from machine learning
The material theory of object-induction and the universal optimality of meta-induction
| Unique citing works | 7 |
|---|---|
| Citations per year | 1.17 |
| Citation span | 2020 - 2025 (6) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 7 |