English
Related papers

Related papers: When AAA Satisfies Nothing: Impossibility Theorems…

200 papers

Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward this goal, and…

Machine Learning · Computer Science 2026-05-12 Jiayi Huang

Conformal prediction is a popular framework of uncertainty quantification that constructs prediction sets with coverage guarantees. To uphold the exchangeability assumption, many conformal prediction methods necessitate an additional…

Machine Learning · Computer Science 2025-07-11 Hao Zeng , Kangdao Liu , Bingyi Jing , Hongxin Wei

An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the…

Artificial Intelligence · Computer Science 2023-06-19 Mario Brcic , Roman V. Yampolskiy

In designed experiments and surveys, known laws or design feat ures provide checks on the most relevant aspects of a model and identify the target parameters. In contrast, in most observational studies in the health and social sciences, the…

Methodology · Statistics 2010-01-18 Sander Greenland

Within the field of Requirements Engineering (RE), the increasing significance of Explainable Artificial Intelligence (XAI) in aligning AI-supported systems with user needs, societal expectations, and regulatory standards has garnered…

Artificial Intelligence · Computer Science 2023-07-27 Barnaby Crook , Maximilian Schlüter , Timo Speith

We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable…

Machine Learning · Computer Science 2026-05-26 Lauri Lovén , Nam Do , Hassan Mehmood , Dinesh Kumar Sah , Sasu Tarkoma

Due to the growing adoption of deep neural networks in many fields of science and engineering, modeling and estimating their uncertainties has become of primary importance. Despite the growing literature about uncertainty quantification in…

Machine Learning · Computer Science 2023-02-15 Brian Staber , Sébastien Da Veiga

Does machine learning and AI ensure that social biases thrive ? This paper aims to analyse this issue. Indeed, as algorithms are informed by data, if these are corrupted, from a social bias perspective, good machine learning algorithms…

Machine Learning · Statistics 2020-11-03 Bertrand K. Hassani

The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While…

Machine Learning · Computer Science 2023-11-15 Brian Barr , Noah Fatsi , Leif Hancox-Li , Peter Richter , Daniel Proano , Caleb Mok

Competitive equilibrium with equal incomes (CEEI) is a well known fair allocation mechanism; however, for indivisible resources a CEEI may not exist. It was shown in [Budish '11] that in the case of indivisible resources there is always an…

Computer Science and Game Theory · Computer Science 2014-10-02 Abraham Othman , Christos Papadimitriou , Aviad Rubinstein

Reputation mechanisms offer an effective alternative to verification authorities for building trust in electronic markets with moral hazard. Future clients guide their business decisions by considering the feedback from past transactions;…

Artificial Intelligence · Computer Science 2011-11-02 B. Faltings , R. Jurca

With the increasing availability of AI-based decision support, there is an increasing need for their certification by both AI manufacturers and notified bodies, as well as the pragmatic (real-world) validation of these systems. Therefore,…

Machine Learning · Computer Science 2019-10-23 Federico Cabitza , Andrea Campagner

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is…

Machine Learning · Computer Science 2019-01-28 Lydia T. Liu , Max Simchowitz , Moritz Hardt

We assess whether AI systems can credibly evaluate investment risk appetite-a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA,…

The goal of algorithmic recourse is to reverse unfavorable decisions (e.g., from loan denial to approval) under automated decision making by suggesting actionable feature changes (e.g., reduce the number of credit cards). To generate…

Machine Learning · Computer Science 2022-11-07 Martin Pawelczyk , Lea Tiyavorabun , Gjergji Kasneci

Credit risk prediction is an effective way of evaluating whether a potential borrower will repay a loan, particularly in peer-to-peer lending where class imbalance problems are prevalent. However, few credit risk prediction models for…

Machine Learning · Computer Science 2018-05-03 Anahita Namvar , Mohammad Siami , Fethi Rabhi , Mohsen Naderpour

This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can…

Software Engineering · Computer Science 2026-01-30 Sankalp Gilda , Shlok Gilda

Decisions suggested by improperly designed software systems might be prone to discriminate against people based on protected characteristics, such as gender and ethnicity. Previous studies attribute such undesired behavior to flaws in…

Software Engineering · Computer Science 2025-09-26 Qusai Ramadan , Jukka Ruohonen , Abhishek Tiwari , Adam Alami , Zeyd Boukhers

In fields that are mainly nonexperimental, such as economics and finance, it is inescapable to compute test statistics and confidence regions that are not probabilistically independent from previously examined data. The Bayesian and…

Statistics Theory · Mathematics 2015-04-20 Benjamin Holcblat , Steffen Grønneberg

Proper scoring rules incentivize experts to accurately report beliefs, assuming predictions cannot influence outcomes. We relax this assumption and investigate incentives when predictions are performative, i.e., when they can influence the…

Artificial Intelligence · Computer Science 2023-05-31 Caspar Oesterheld , Johannes Treutlein , Emery Cooper , Rubi Hudson
‹ Prev 1 8 9 10 Next ›