English
Related papers

Related papers: Escaping Arrow's Theorem: The Advantage-Standard M…

200 papers

Utility functions or their equivalents (value functions, objective functions, loss functions, reward functions, preference orderings) are a central tool in most current machine learning systems. These mechanisms for defining goals and…

Artificial Intelligence · Computer Science 2019-03-06 Peter Eckersley

The Availability bias, manifested in the over-representation of extreme eventualities in decision-making, is a well-known cognitive bias, and is generally taken as evidence of human irrationality. In this work, we present the first…

Neurons and Cognition · Quantitative Biology 2018-01-31 Ardavan S. Nobandegani , Kevin da Silva Castanheira , A. Ross Otto , Thomas R. Shultz

As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these tasks, which we refer to as ''AI Oversight''. We study how…

Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for active learning as an efficient method to iteratively construct…

Human-Computer Interaction · Computer Science 2024-07-29 Vijay Keswani , Vincent Conitzer , Hoda Heidari , Jana Schaich Borg , Walter Sinnott-Armstrong

Fundamental choice axioms, such as transitivity of preference, provide testable conditions for determining whether human decision making is rational, i.e., consistent with a utility representation. Recent work has demonstrated that AI…

Artificial Intelligence · Computer Science 2025-02-18 Kiwon Song , James M. Jennings , Clintin P. Davis-Stober

The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and (3) that AI systems…

Artificial Intelligence · Computer Science 2024-11-12 Tan Zhi-Xuan , Micah Carroll , Matija Franklin , Hal Ashton

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…

Machine Learning · Computer Science 2024-05-07 Ang Li , Yifei Wang , Yiwen Guo , Yisen Wang

This paper analyzes the asymptotic performance of two popular affirmative action policies, majority quota and minority reserve, under the immediate acceptance mechanism (IAM) and the top trading cycles mechanism (TTCM) in the contest of…

Theoretical Economics · Economics 2022-12-13 Di Feng , Yun Liu

How do we compare between hypotheses that are entirely consistent with observations? The marginal likelihood (aka Bayesian evidence), which represents the probability of generating our observations from a prior, provides a distinctive…

Machine Learning · Computer Science 2023-05-03 Sanae Lotfi , Pavel Izmailov , Gregory Benton , Micah Goldblum , Andrew Gordon Wilson

Recent work on the logical structure of non-locality has constructed scenarios where observations of multi-partite systems cannot be adequately described by compositions of non-signaling subsystems. In this paper we apply these frameworks…

Computer Science and Game Theory · Computer Science 2015-12-10 William Zeng , Philipp Zahn

We consider voting on multiple independent binary issues. In addition, a weighting vector for each voter defines how important they consider each issue. The most natural way to aggregate the votes into a single unified proposal is…

Computer Science and Game Theory · Computer Science 2025-02-21 Carmel Baharav , Andrei Constantinescu , Roger Wattenhofer

We study a contest-theoretic model of adversarial investment in which an attacker and a defender allocate resources to AI-augmented capabilities across multiple attack surfaces. The attacker's investment operates through two channels: it…

Theoretical Economics · Economics 2026-05-18 James W. Bono

Non-concave penalized maximum likelihood methods, such as the Bridge, the SCAD, and the MCP, are widely used because they not only do parameter estimation and variable selection simultaneously but also have a high efficiency as compared to…

Methodology · Statistics 2015-12-31 Yuta Umezu , Yusuke Shimizu , Hiroki Masuda , Yoshiyuki Ninomiya

Quota-based fairness mechanisms like the so-called Rooney rule or four-fifths rule are used in selection problems such as hiring or college admission to reduce inequalities based on sensitive demographic attributes. These mechanisms are…

Computers and Society · Computer Science 2020-06-25 Vitalii Emelianov , Nicolas Gast , Krishna P. Gummadi , Patrick Loiseau

The Lasso method is known to exhibit instability in the presence of highly correlated features, often leading to an arbitrary selection of predictors. This issue manifests itself in two primary error types: the erroneous omission of…

Methodology · Statistics 2025-08-07 Yanxin Liu , Yunqi Zhang

Actuarial risk assessments might be unduly perceived as a neutral way to counteract implicit bias and increase the fairness of decisions made at almost every juncture of the criminal justice system, from pretrial release to sentencing,…

Machine Learning · Computer Science 2018-07-17 Chelsea Barabas , Karthik Dinakar , Joichi Ito , Madars Virza , Jonathan Zittrain

Multiwinner voting rules can be used to select a fixed-size committee from a larger set of candidates. We consider approval-based committee rules, which allow voters to approve or disapprove candidates. In this setting, several voting rules…

Computer Science and Game Theory · Computer Science 2024-11-05 Dominik Peters

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil

Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement errors -- stochastic fluctuations that manifest as preference…

Artificial Intelligence · Computer Science 2026-05-26 Boyin Liu , Zhuo Zhang , Sen Huang , Lipeng Xie , Qingxu Fu , Haoran Chen , LI YU , Tianyi Hu , Zhaoyang Liu , Bolin Ding , Dongbin Zhao

In Terao [24], Hiroaki Terao defined and studied "admissible map", which is a generalization of "social welfare function" in the context of hyperplane arrangements. Using this, he proved a generalized Arrow's Impossibility Theorem using…

Combinatorics · Mathematics 2024-08-27 Takuma Okura
‹ Prev 1 8 9 10 Next ›