MCMP – Mathematical Philosophy (Archive 2011/12)

Tracking the Truth Requires a Non-wellfounded Prior!


Listen Later

Alexandru Baltag (ILLC Amsterdam) gives a talk at the MCMP Colloquium titled "Tracking the Truth Requires a Non-wellfounded Prior! A Study in the Learning Power (and Limits) of Bayesian (and Qualitative) Update". Abstract: The talk is about tracking "full truth" in the limit by iterated belief updates. Unlike Sonja's talk (which focused on finite models), we now allow the initial model (and thus the initial set of epistemic possibilities) to be infinite. We compare the truth-tracking power of various belief-revision methods, including probabilistic conditioning (also known as Bayesian update) and some of its qualitative, "plausibilistic" analogues (conditioning, lexicographic revision, minimal revision). We focus in particular on the question on whether any of these methods is "universal" (i.e. as good at tracking the truth as any other learning method). We show that this is not the case, as long as we keep the standard probabilistic (or belief-revision) setting. On the positive side, we show that if we consider appropriate generalizations of conditioning in a non-standard, non-wellfounded setting, then universality is achieved for some (though not all) of these learning methods. In the qualitative case, this means that we need to allow the prior plausibility relation to be a non-wellfounded (though total) preorder. In the probabilistic case, this means moving to a generalized conditional probability setting, in which the family of "cores" (or "strong beliefs") may be non-wellfounded (when ordered by inclusion or logical entailament). As a consequence, neither the family of classical probability spaces, nor lexicographic probability spaces, and not even the family of all countably additive (conditional) probability spaces, are rich enough to make Bayesian conditioning "universal", from a Learning Theoretic point of view! This talk is based on joint work with Nina Gierasimczuk and Sonja Smets.
...more
View all episodesView all episodes
Download on the App Store

MCMP – Mathematical Philosophy (Archive 2011/12)By MCMP Team

  • 5
  • 5
  • 5
  • 5
  • 5

5

6 ratings


More shows like MCMP – Mathematical Philosophy (Archive 2011/12)

View all
Hegel lectures by Robert Brandom, LMU Munich by Robert Brandom, Axel Hutter

Hegel lectures by Robert Brandom, LMU Munich

6 Listeners

LMU Fakultät für Philosophie, Wissenschaftstheorie und Religionswissenschaft - Vorlesungen und Vorträge by Professoren der Fakultät für Philosophie, Wissenschaftstheorie und Religionswissenschaft

LMU Fakultät für Philosophie, Wissenschaftstheorie und Religionswissenschaft - Vorlesungen und Vorträge

0 Listeners

John Lennox - Hat die Wissenschaft Gott begraben? by Professor John C. Lennox, University of Oxford

John Lennox - Hat die Wissenschaft Gott begraben?

3 Listeners

MCMP – Philosophy of Science by MCMP Team

MCMP – Philosophy of Science

2 Listeners

Epistemology and Philosophy of Science: Prof. Dr. Stephan Hartmann – HD by Ludwig-Maximilians-Universität München

Epistemology and Philosophy of Science: Prof. Dr. Stephan Hartmann – HD

1 Listeners

MCMP – Philosophy of Physics by MCMP Team

MCMP – Philosophy of Physics

3 Listeners

Sommerfeld Lecture Series (ASC) by The Arnold Sommerfeld Center for Theoretical Physics (ASC)

Sommerfeld Lecture Series (ASC)

0 Listeners

MCMP by MCMP Team

MCMP

2 Listeners

Women Thinkers in Antiquity and the Middle Ages - SD by Peter Adamson

Women Thinkers in Antiquity and the Middle Ages - SD

0 Listeners

Ukraine: The Latest by The Telegraph

Ukraine: The Latest

1,749 Listeners