Learning by Ignoring the Most Wrong
Open Access
- 24 December 2021
- journal article
- research article
- Published by Walter de Gruyter GmbH in KRITERION – Journal of Philosophy
- Vol. 36 (1) , 9-31
Abstract
Imprecise probabilities (IP) are an increasingly popular way of reasoning about rational credence. However they are subject to an apparent failure to display convincing inductive learning. This paper demonstrates that a small modification to the update rule for IP allows us to overcome this problem, albeit at the cost of satisfying only a weaker concept of coherence.Keywords
Funding Information
- Horizon 2020 Framework Programme (792292)
This publication has 36 references indexed in Scilit:
- A DEFENSE OF IMPRECISE CREDENCES IN INFERENCE AND DECISION MAKING1Philosophical Perspectives, 2010
- THE AMBIGUITY AVERSION LITERATURE: A CRITICAL ASSESSMENTEconomics and Philosophy, 2009
- Updating coherent previsions on finite spacesFuzzy Sets and Systems, 2009
- Arguments for–or against–Probabilism?The British Journal for the Philosophy of Science, 2008
- How Probabilities Reflect EvidencePhilosophical Perspectives, 2005
- What Conditional Probability Could Not BeSynthese, 2003
- Dilation for Sets of ProbabilitiesThe Annals of Statistics, 1993
- Updating Ambiguous BeliefsJournal of Economic Theory, 1993
- An approach to consensus and certainty with increasing evidenceJournal of Statistical Planning and Inference, 1990
- On Indeterminate ProbabilitiesThe Journal of Philosophy, 1974