Probing the quantitative–qualitative divide in probabilistic reasoning

Annals of Pure and Applied Logic · 2023 · 11 citations

• Computer Science
• Artificial Intelligence
• Computer Science

This paper explores the space of (propositional) probabilistic logical languages, ranging from a purely ‘qualitative’ comparative language to a highly ‘quantitative’ language involving arbitrary polynomials over probability terms. While talk of qualitative vs. quantitative may be suggestive, we identify a robust and meaningful boundary in the space by distinguishing systems that encode (at most) additive reasoning from those that encode additive and multiplicative reasoning. The latter includes not only languages with explicit multiplication but also languages expressing notions of dependence and conditionality. We show that the distinction tracks a divide in computational complexity: additive systems remain complete for NP, while multiplicative systems are robustly complete for ∃R. We also address axiomatic questions, offering several new completeness results as well as a proof of non-finite-axiomatizability for comparative probability. Repercussions of our results for conceptual and empirical questions are addressed, and open problems are discussed.

On Pearl’s Hierarchy and the Foundations of Causal Inference

ACM eBooks · 2022 · 139 citations

• Computer Science
• Artificial Intelligence
• Political Science

chapter Share on On Pearl's Hierarchy and the Foundations of Causal Inference Authors: Elias Bareinboim Columbia University Columbia UniversitySearch about this author , Juan D. Correa Columbia University Columbia UniversitySearch about this author , Duligur Ibeling Stanford University Stanford UniversitySearch about this author , Thomas Icard Stanford University Stanford UniversitySearch about this author Authors Info & Claims Probabilistic and Causal Inference: The Works of Judea PearlFebruary 2022 Pages 507–556https://doi.org/10.1145/3501714.3501743Online:04 March 2022Publication History 0citation26DownloadsMetricsTotal Citations0Total Downloads26Last 12 Months26Last 6 weeks6 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

On the Opportunities and Risks of Foundation Models

arXiv (Cornell University) · 2021 · 2169 citations

• Computer Science
• Artificial Intelligence
• Computer Science

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.