English
Related papers

Related papers: Is Arrow's Dictator a Drinker?

200 papers

Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a…

Computation and Language · Computer Science 2025-08-19 Noah Kasmanoff , Rahul Zalkikar

In this paper we provide a theoretical analysis of counterfactual invariance. We present a variety of existing definitions, study how they relate to each other and what their graphical implications are. We then turn to the current major…

Machine Learning · Computer Science 2023-07-18 Jake Fawkes , Robin J. Evans

The question of whether AI systems have morally relevant interests -- the 'model welfare' question -- depends in part on how we evaluate AI testimony about inner states. This paper develops what I call the inconsistency critique:…

Computers and Society · Computer Science 2026-01-15 Gerol Petruzella

The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracted as a higher-level algorithm if there exists a function…

Machine Learning · Computer Science 2025-11-13 Denis Sutter , Julian Minder , Thomas Hofmann , Tiago Pimentel

We introduce a new decentralized observation condition which we call "at least one can tell" (OCT) and which attempts to capture the idea that for any possible behavior that a system can generate, at least one decentralized observation…

Formal Languages and Automata Theory · Computer Science 2021-08-11 Stavros Tripakis , Karen Rudie

We generalize the Arrow's impossibility theorem--a key result in social choice theory--to the setting where the arity $k$ of the relation under consideration is greater than $2$. Some special but natural properties of $k$-ary relations are…

Logic · Mathematics 2019-04-30 Harshit Bisht , Amit Kuber

In this letter, we point out that the widely used quantitative conditions in the adiabatic theorem are insufficient in that they do not guarantee the validity of the adiabatic approximation. We also reexamine the inconsistency issue raised…

Quantum Physics · Physics 2009-11-11 D. M. Tong , K. Singh , L. C. Kwek , C. H. Oh

We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes current interpretability research fundamentally ill-posed.…

Machine Learning · Computer Science 2025-08-04 Pietro Barbiero , Mateo Espinosa Zarlenga , Alberto Termine , Mateja Jamnik , Giuseppe Marra

The paper continues the authors' study of the linearizability problem for nonlinear control systems. In the recent work [K. Sklyar, Systems Control Lett. 134 (2019), 104572], conditions on mappability of a nonlinear control system to a…

Optimization and Control · Mathematics 2021-01-26 Katerina V. Sklyar , Svetlana Yu. Ignatovich

We derive sufficient conditions for the solvability of the observer design problem for a wide class of nonlinear time-varying systems, including those having triangular structure. We establish that, under weaker assumptions than those…

Optimization and Control · Mathematics 2011-11-03 D. Boskos , J. Tsinias

To make accurate inferences in an interactive setting, an agent must not confuse passive observation of events with having intervened to cause them. The $do$ operator formalises interventions so that we may reason about their effect. Yet…

Artificial Intelligence · Computer Science 2024-04-12 Michael Timothy Bennett

It is argued that systematically unbiassing estimators is not always justified and can be counter-productive. On the contrary, a general rule is given to build a (slightly) biased but consistent estimator which is always closer to the value…

High Energy Physics - Phenomenology · Physics 2007-05-23 Jean-Michel Levy

Hypothetical Datalog is based on an intuitionistic semantics rather than on a classical logic semantics, and embedded implications are allowed in rule bodies. While the usual implication (i.e., the neck of a Horn clause) stands for…

Databases · Computer Science 2015-12-23 Fernando Sáenz-Pérez

We address the issue of the testability of instrumental variables derived from observational data. Most existing testable implications are centered on scenarios where the treatment is a discrete variable, e.g., instrumental inequality…

Methodology · Statistics 2026-03-13 Xichen Guo , Zheng Li , Biwei Huang , Yan Zeng , Zhi Geng , Feng Xie

Knowing the norms of a domain is crucial, but there exist no repository of norms. We propose a method to extract them from texts: texts generally do not describe a norm, but rather how a state-of-affairs differs from it. Answers concerning…

Artificial Intelligence · Computer Science 2007-05-23 Daniel Kayser , Farid Nouioua

We say that a theory $T$ is intermediate under effective reducibility if the isomorphism problems among its computable models is neither hyperarithmetic nor on top under effective reducibility. We prove that if an infinitary sentence $T$ is…

Logic · Mathematics 2013-09-17 Antonio Montalbán

In this paper, we provide more evidence for the contention that logical consequence should be understood in normative terms. Hartry Field and John MacFarlane covered the classical case. We extend their work, examining what it means for an…

Logic in Computer Science · Computer Science 2014-02-20 Julio Lemos

We analyze a class of modal logics rendered insensitive to reflexivity by way of a modification to the semantic definition of the modal operator. We explore the extent to which these logics can be characterized, and prove a general…

Logic · Mathematics 2019-02-20 David Gilbert , Giorgio Venturi

Can artificially intelligent systems follow rules? The answer might seem an obvious `yes', in the sense that all (current) AI strictly acts in accordance with programming code constructed from highly formalized and well-defined rulesets.…

Artificial Intelligence · Computer Science 2021-10-27 John Licato

We identify a fundamental incompatibility between the goals of accuracy, trust, and human-level reasoning in artificial intelligence (AI) systems, for strict mathematical definitions of these notions. We define accuracy of a system as the…

Machine Learning · Computer Science 2026-05-11 Rina Panigrahy , Vatsal Sharan
‹ Prev 1 8 9 10 Next ›