Kevin T. Kelly
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Kevin T. Kelly has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Conor Mayo-Wilson
Department of Philosophy Carnegie Mellon University Baker Hall 135, Pittsburgh PA 15213-3890
2 shared publications - Hanti Lin
Carnegie Mellon University
2 shared publications - Konstantin Genin
Carnegie Mellon University
2 shared publications - Hanti Lin
University of California Davis
1 shared publication - Konstantin Genin
Carnegie Mellon University, Pittsburgh, USA
1 shared publication
Latest Publications
- 4 August 2018
- Published by Springer Nature in Studia Logica
- Vol. 107 (5) , 949-989
Theory Choice, Theory Change, and Inductive Truth-Conduciveness
- 4 August 2018
- Published by Springer Nature in Studia Logica
- Vol. 107 (5) , 949-989
Theory Choice, Theory Change, and Inductive Truth-Conduciveness
- Open Access
- 25 July 2017
- Published by Open Publishing Association in Electronic Proceedings in Theoretical Computer Science
- Vol. 251, 236-250
The Topology of Statistical Verifiability
Topological models of empirical and formal inquiry are increasingly prevalent. They have emerged in such diverse fields as domain theory [1, 16], formal learning theory [18], epistemology and philosophy of science [10, 15, 8, 9, 2], statistics [6, 7] and modal logic [17, 4]. In those applications, open sets are typically interpreted as hypotheses deductively verifiable by true propositional information that rules out relevant possibilities. However, in statistical data analysis, one routinely receives random samples logically compatible with every statistical hypothesis. We bridge the gap between propositional and statistical data by solving for the unique topology on probability measures in which the open sets are exactly the statistically verifiable hypotheses. Furthermore, we extend that result to a topological characterization of learnability in the limit from statistical data.Comment: In Proceedings TARK 2017, arXiv:1707.0825
- 25 July 2017
- Published by Open Publishing Association in Electronic Proceedings in Theoretical Computer Science
- Vol. 251, 236-250
Open AccessThe Topology of Statistical Verifiability
Topological models of empirical and formal inquiry are increasingly prevalent. They have emerged in such diverse fields as domain theory [1, 16], formal learning theory [18], epistemology and philosophy of science [10, 15, 8, 9, 2], statistics [6, 7] and modal logic [17, 4]. In those applications, open sets are typically interpreted as hypotheses deductively verifiable by true propositional information that rules out relevant possibilities. However, in statistical data analysis, one routinely receives random samples logically compatible with every statistical hypothesis. We bridge the gap between propositional and statistical data by solving for the unique topology on probability measures in which the open sets are exactly the statistically verifiable hypotheses. Furthermore, we extend that result to a topological characterization of learnability in the limit from statistical data.Comment: In Proceedings TARK 2017, arXiv:1707.0825
- 15 April 2016
- Published by Springer Nature in Synthese
- Vol. 193 (4) , 1191-1223
Realism, rhetoric, and reliability
- 15 April 2016
- Published by Springer Nature in Synthese
- Vol. 193 (4) , 1191-1223
Realism, rhetoric, and reliability
- 27 August 2014
- Published by Springer Nature
- p. 289-337
A Computational Learning Semantics for Inductive Empirical Knowledge
- 27 August 2014
- Published by Springer Nature
- p. 289-337
A Computational Learning Semantics for Inductive Empirical Knowledge
- 29 June 2012
- Published by Springer Nature in Journal of Philosophical Logic
- Vol. 41 (6) , 957-981
Propositional Reasoning that Tracks Probabilistic Reasoning
- 29 June 2012
- Published by Springer Nature in Journal of Philosophical Logic
- Vol. 41 (6) , 957-981
Propositional Reasoning that Tracks Probabilistic Reasoning
- Open Access
Causal Conclusions that Flip Repeatedly and Their Justification
Over the past two decades, several consistent procedures have been designed to infer causal conclusions from observational data. We prove that if the true causal network might be an arbitrary, linear Gaussian network or a discrete Bayes network, then every unambiguous causal conclusion produced by a consistent method from non-experimental data is subject to reversal as the sample size increases any finite number of times. That result, called the causal flipping theorem, extends prior results to the effect that causal discovery cannot be reliable on a given sample size. We argue that since repeated flipping of causal conclusions is unavoidable in principle for consistent methods, the best possible discovery methods are consistent methods that retract their earlier conclusions no more than necessary. A series of simulations of various methods across a wide range of sample sizes illustrates concretely both the theorem and the principle of comparing methods in terms of retractions.
Open AccessCausal Conclusions that Flip Repeatedly and Their Justification
Over the past two decades, several consistent procedures have been designed to infer causal conclusions from observational data. We prove that if the true causal network might be an arbitrary, linear Gaussian network or a discrete Bayes network, then every unambiguous causal conclusion produced by a consistent method from non-experimental data is subject to reversal as the sample size increases any finite number of times. That result, called the causal flipping theorem, extends prior results to the effect that causal discovery cannot be reliable on a given sample size. We argue that since repeated flipping of causal conclusions is unavoidable in principle for consistent methods, the best possible discovery methods are consistent methods that retract their earlier conclusions no more than necessary. A series of simulations of various methods across a wide range of sample sizes illustrates concretely both the theorem and the principle of comparing methods in terms of retractions.
- 6 September 2011
- Published by Springer Nature in Synthese
- Vol. 186 (2) , 531-575
A geo-logical solution to the lottery paradox, with applications to conditional logic
- 6 September 2011
- Published by Springer Nature in Synthese
- Vol. 186 (2) , 531-575
A geo-logical solution to the lottery paradox, with applications to conditional logic
- 24 August 2010
- Published by Springer Nature in Journal of Philosophical Logic
- Vol. 39 (6) , 679-712
Ockham Efficiency Theorem for Stochastic Empirical Methods
- 24 August 2010
- Published by Springer Nature in Journal of Philosophical Logic
- Vol. 39 (6) , 679-712
Ockham Efficiency Theorem for Stochastic Empirical Methods
- 1 January 2007
- Published by Springer Nature
- p. 199-217
How to Do Things with an Infinite Regress