Schurz, Gerhard (2016) No Free Lunch Theorem, Inductive Skepticism, and the Optimality of Meta-Induction. In: UNSPECIFIED.

Preview

Text NoFreeeLunchPSArchive.pdf Download (73kB) | Preview

Abstract

The no free lunch theorem (Wolpert 1996) 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 (Schurz 2008). 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 paper this conflict is analyzed and dissolved, by means of probabilistic analysis and computer simulation.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Creators:	Creators Email ORCID Schurz, Gerhard
Keywords:	No free lunch theorem, inductive skepticism, optimality of meta-induction
Subjects:	General Issues > Confirmation/Induction General Issues > Formal Learning Theory
Depositing User:	Gerhard Schurz
Date Deposited:	29 Oct 2016 16:40
Last Modified:	29 Oct 2016 16:40
Item ID:	12540
Subjects:	General Issues > Confirmation/Induction General Issues > Formal Learning Theory
Date:	28 October 2016
URI:	https://philsci-archive.pitt.edu/id/eprint/12540

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item