English
Related papers

Related papers: Which causality? Differences between the trajector…

200 papers

Some recent works observed the instability of post-hoc explanations when input side perturbations are applied to the model. This raises the interest and concern in the stability of post-hoc explanations. However, the remaining question is:…

Computation and Language · Computer Science 2022-12-13 Ruixuan Tang , Hanjie Chen , Yangfeng Ji

Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question of explaining predictive uncertainty, i.e. why a model…

Machine Learning · Computer Science 2024-11-19 Florian Bley , Sebastian Lapuschkin , Wojciech Samek , Grégoire Montavon

Quantum Mechanics (QM) stands alone as a (very) successful physical theory, but the meaning of its variables and the status of many quantities in the mathematical formalism is obscure. This unique situation prompted the need for attribution…

Quantum Physics · Physics 2023-03-28 Jorge E. Horvath , Rodrigo Rosas Fernandes

A thought experiment is described and the probability of a particular type of results is predicted according to the quantum formalism. Then, the assumption is made that there exists a particle that travels from the source to one of the…

General Physics · Physics 2022-07-21 Sofia Wechsler

In an exact quantum-mechanical framework, we show that expectation values of the second-quantized electro-magnetic fields in the Coulomb gauge, and in the presence of classical sources, automatically lead to causal and retarded…

Quantum Physics · Physics 2019-04-02 Bo-Sture K. Skagerstam , Karl-Erik Eriksson , Per K. Rekdal

The ability to distinguish between correlation and causation of variables in molecular systems remains an interesting and open area of investigation. In this work, we probe causality in a molecular system using two independent computational…

Chemical Physics · Physics 2025-02-27 Vittorio Del Tatto , Debarshi Banerjee , Ali Hassanali , Alessandro Laio

In the context of abstract argumentation, we present the benefits of considering temporality, i.e. the order in which arguments are enunciated, as well as causality. We propose a formal method to rewrite the concepts of acyclic abstract…

Artificial Intelligence · Computer Science 2024-02-07 Y. Munro , C. Sarmiento , I. Bloch , G. Bourgne , M. -J. Lesot

Orthodox Copenhagen quantum theory renounces the quest to understand the reality in which we are imbedded, and settles for practical rules that describe connections between our observations. However, an examination of certain nonlocal…

Quantum Physics · Physics 2007-05-23 Henry P. Stapp

The effects of three-dimensional perturbations in two-dimensional turbulence are investigated, through a conformal field theory approach. We compute scaling exponents for the energy spectra of enstrophy and energy cascades, in a strong…

High Energy Physics - Theory · Physics 2009-10-28 L. Moriconi

This paper presents a formal approach to explaining change of inference in Quantitative Bipolar Argumentation Frameworks (QBAFs). When drawing conclusions from a QBAF and updating the QBAF to then again draw conclusions (and so on), our…

Artificial Intelligence · Computer Science 2025-09-24 Timotheus Kampik , Kristijonas Čyras , José Ruiz Alarcón

Structural causal models postulate noisy functional relations among a set of interacting variables. The causal structure underlying each such model is naturally represented by a directed graph whose edges indicate for each variable which…

Statistics Theory · Mathematics 2022-03-15 David Strieder , Tobias Freidling , Stefan Haffner , Mathias Drton

We treat two aspects of the physics of stationary black holes. First we prove that the proportionality, d(energy) ~ d(area) for arbitrary perturbations (``extended first law''), follows directly from an extremality theorem drawn from…

General Relativity and Quantum Cosmology · Physics 2007-05-23 Rafael D. Sorkin

Many research questions involve time-to-event outcomes that can be prevented from occurring due to competing events. In these settings, we must be careful about the causal interpretation of classical statistical estimands. In particular,…

Methodology · Statistics 2020-09-01 Torben Martinussen , Mats Julius Stensrud

Humans have a remarkable ability to use physical commonsense and predict the effect of collisions. But do they understand the underlying factors? Can they predict if the underlying factors have changed? Interestingly, in most cases humans…

Computer Vision and Pattern Recognition · Computer Science 2018-08-31 Tian Ye , Xiaolong Wang , James Davidson , Abhinav Gupta

Understanding causal mechanisms across different populations is essential for designing effective public health interventions. Recently, difference graphs have been introduced as a tool to visually represent causal variations between two…

Artificial Intelligence · Computer Science 2025-02-18 Charles K. Assaad

We present a definition of cause and effect in terms of decision-theoretic primitives and thereby provide a principled foundation for causal reasoning. Our definition departs from the traditional view of causation in that causal assertions…

Artificial Intelligence · Computer Science 2014-11-17 D. Heckerman , R. Shachter

Causality is pivotal to our understanding of the world, presenting itself in different forms: information-theoretic and relativistic, the former linked to the flow of information, the latter to the structure of space-time. Leveraging a…

General Relativity and Quantum Cosmology · Physics 2026-04-13 Maarten Grothus , V. Vilasini

A causality problem in the time-dependent scattering of classical waves from point scatterers is pointed out and analyzed. Based on an alternative model, the leading pole approximation of the exact scattering matrix of the square well…

Mesoscale and Nanoscale Physics · Physics 2009-11-07 Gerrit E. W. Bauer , Mauro S. Ferreira , Cees P. A. Wapenaar

Linear approximations to the decision boundary of a complex model have become one of the most popular tools for interpreting predictions. In this paper, we study such linear explanations produced either post-hoc by a few recent methods or…

Machine Learning · Computer Science 2018-01-31 Maruan Al-Shedivat , Avinava Dubey , Eric P. Xing

Most traditional models of uncertainty have focused on the associational relationship among variables as captured by conditional dependence. In order to successfully manage intelligent systems for decision making, however, we must be able…

Artificial Intelligence · Computer Science 2015-05-19 David Heckerman , Ross D. Shachter
‹ Prev 1 8 9 10 Next ›