Results 11 to 20 of about 43,008 (285)
Advances in Neural Information Processing Systems 35, 2022 To act safely and ethically in the real world, agents must be able to reason about harm and avoid harmful actions. However, to date there is no statistical method for measuring harm and factoring it into algorithmic decisions. In this paper we propose the first formal definition of harm and benefit using causal models.
Jonathan G. Richens +2 more
openaire +3 more sources
Counterfactual: An R Package for Counterfactual Analysis [PDF]
The R Journal, 2017 15 pages, 4 ...
Chen, Mingli +3 more
openaire +5 more sources
Counterfactual Desirability [PDF]
The British Journal for the Philosophy of Science, 2017 The desirability of what actually occurs is often influenced by what could have been. Preferences based on such value dependencies between actual and counterfactual outcomes generate a class of problems for orthodox decision theory, the best-known perhaps being the so-called Allais paradox.
Bradley, Richard, Stefánsson, H. Orri
openaire +2 more sources
CoRR, 2022 2nd Conference on Causal Learning and Reasoning (CLeaR 2023) (minor formatting changes from conference camera ready version)
Julius von Kügelgen +2 more
openaire +6 more sources
EQUILIBRIUM COUNTERFACTUALS [PDF]
International Economic Review, 2019 AbstractWe incorporate structural modelers into the economy they model. Using traditional moment matching, they treat policy changes as zero probability (or exogenous) “counterfactuals.” Bias occurs since real‐world agents understand policy changes are positive probability events guided by modelers. Downward, upward, or sign bias occurs.
Gilles Chemla, Christopher Hennessy
openaire +3 more sources
Counterfactuality of ‘counterfactual’ communication [PDF]
Journal of Physics A: Mathematical and Theoretical, 2014 Critical analysis of arXiv:1206.2042 and Phys. Rev. A 89, 052334. Revised according to comments of several referees, accepted for publication in J.
openaire +2 more sources
Evaluation of counterfactuality in counterfactual communication protocols [PDF]
Physical Review A, 2017 We provide an in-depth investigation of parameter estimation in nested Mach-Zehnder interferometers (NMZIs) using two information measures: the Fisher information and the Shannon mutual information. Protocols for counterfactual communication have, so far, been based on two different definitions of counterfactuality.
Arvidsson-Shukur, DRM +2 more
openaire +3 more sources
Findings of the Association for Computational Linguistics: ACL 2023, 2023 In the wake of responsible AI, interpretability methods, which attempt to provide an explanation for the predictions of neural models have seen rapid progress. In this work, we are concerned with explanations that are applicable to natural language processing (NLP) models and tasks, and we focus specifically on the analysis of counterfactual ...
George Filandrianos +4 more
openaire +2 more sources
COUNTERFACTUAL ANALYSIS BY ALGORITHMIC COMPLEXITY: A METRIC BETWEEN POSSIBLE WORLDS
Manuscrito, 2022 Counterfactuals have become an important area of interdisciplinary interest, especially in logic, philosophy of language, epistemology, metaphysics, psychology, decision theory, and even artificial intelligence.
NICHOLAS CORRÊA +1 more
doaj +1 more source
Notre Dame Journal of Formal Logic, 1975 The inclusion of the formulae \((A > B) \vee (A> -B)\) and \((A \& B) \supset(A> B)\) as theorems of conditional sentential calculi is criticised and reasons are offered for including \(\square(A\supset B)\supset . (B> C) \supset . \diamond (A \& C) \supset .(A> C)\) as a theorem in such calculi.
openaire +3 more sources