English
Related papers

Related papers: Reputational Conservatism in Expert Advice

200 papers

This paper proposes a way of protecting probabilistic prediction models against changes in the data distribution, concentrating on the case of classification and paying particular attention to binary classification. This is important in…

Machine Learning · Computer Science 2021-10-26 Vladimir Vovk , Ivan Petej , Alex Gammerman

Cooperation is a crucial aspect of social life, yet understanding the nature of cooperation and how it can be promoted is an ongoing challenge. One mechanism for cooperation is indirect reciprocity. According to this mechanism, individuals…

Populations and Evolution · Quantitative Biology 2023-08-30 Yohsuke Murase , Christian Hilbe

We propose and analyze a family of information processing systems, where a finite set of experts or servers are employed to extract information about a stream of incoming jobs. Each job is associated with a hidden label drawn from some…

Probability · Mathematics 2016-05-31 Laurent Massoulie , Kuang Xu

I revisit the standard moral-hazard model, in which an agent's preference over contracts is rooted in costly effort choice. I characterise the behavioural content of the model in terms of empirically testable axioms, and show that the…

Theoretical Economics · Economics 2025-11-26 Ludvig Sinander

When dealing with time series with complex non-stationarities, low retrospective regret on individual realizations is a more appropriate goal than low prospective risk in expectation. Online learning algorithms provide powerful guarantees…

Machine Learning · Statistics 2011-06-30 Cosma Rohilla Shalizi , Abigail Z. Jacobs , Kristina Lisa Klinkner , Aaron Clauset

Social scientists have long sought to understand why certain people, items, or options become more popular than others. One seemingly intuitive theory is that inherent value drives popularity. An alternative theory claims that popularity is…

Social and Information Networks · Computer Science 2015-02-02 Peter Krafft , Julia Zheng , Erez Shmueli , Nicolás Della Penna , Josh Tenenbaum , Sandy Pentland

There has been great interest in fairness in machine learning, especially in relation to classification problems. In ranking-related problems, such as in online advertising, recommender systems, and HR automation, much work on fairness…

Machine Learning · Computer Science 2025-04-21 Andrii Kliachkin , Eleni Psaroudaki , Jakub Marecek , Dimitris Fotakis

This paper studies preference aggregation under risk. In our model, each agent has an incomplete preference relation represented by a set of expected utility functions. The classical Pareto principle is silent on agreement involving…

Theoretical Economics · Economics 2026-01-06 Leo Kurata , Kensei Nakamura

Public opinion on recommender systems has become increasingly wary in recent years. In line with this trend, lawmakers have also started to become more critical of such systems, resulting in the introduction of new laws focusing on aspects…

Human-Computer Interaction · Computer Science 2024-10-02 Roan Schellingerhout

In business, politics and life, folk wisdom encourages people to aim for above-average results, but to not let the perfect be the enemy of the good. Here, we mathematically formalize and extend this folk wisdom. We model a time-limited…

Physics and Society · Physics 2026-02-11 Ekaterina Landgren , Ryan E. Langendorf , Matthew G. Burgess

The fundamental principle in Modern Portfolio Theory (MPT) is based on the quantification of the portfolio's risk related to performance. Although MPT has made huge impacts on the investment world and prompted the success and prevalence of…

Portfolio Management · Quantitative Finance 2021-02-15 Shi Yu , Haoran Wang , Chaosheng Dong

This work studies external regret in sequential prediction games with both positive and negative payoffs. External regret measures the difference between the payoff obtained by the forecasting strategy and the payoff of the best action. In…

Statistics Theory · Mathematics 2007-06-13 Nicolo Cesa-Bianchi , Yishay Mansour , Gilles Stoltz

Social epistemologists have argued that high risk, high reward science has an important role to play in scientific communities. Recently, though, it has also been argued that various scientific fields seem to be trending towards…

Digital Libraries · Computer Science 2019-10-14 Cailin O'Connor

The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action while the environment simultaneously chooses an outcome. The…

Machine Learning · Computer Science 2024-05-17 Maxime Heuillet , Ola Ahmad , Audrey Durand

We consider a community of users who must make periodic decisions about whether to interact with one another. We propose a protocol which allows honest users to reliably interact with each other, while limiting the damage done by each…

Computer Science and Game Theory · Computer Science 2014-11-06 Paul Christiano

A benevolent advisor observes a project's complexity and posts a pass - fail threshold before the agent chooses effort. The project succeeds only if ability and effort together clear complexity. We compare two informational regimes. In the…

Theoretical Economics · Economics 2025-09-08 Georgy Lukyanov , Mark Izgarshev

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Machine Learning · Computer Science 2025-12-05 Andreas Schlaginhaufen , Reda Ouhamma , Maryam Kamgarpour

Multi-agent reinforcement learning serves as an effective tool for studying strategy adaptation in evolutionary games. Although prior work has integrated Q-learning with reputation mechanisms to promote cooperation, most existing algorithms…

Computational Physics · Physics 2026-04-10 An Li , Wenqiang Zhu , Chaoqian Wang , Longzhao Liu , Hongwei Zheng , Yishen Jiang , Xin Wang , Shaoting Tang

Working under a model of privacy in which data remains private even from the statistician, we study the tradeoff between privacy guarantees and the risk of the resulting statistical estimators. We develop private versions of classical…

Statistics Theory · Mathematics 2017-11-16 John Duchi , Martin Wainwright , Michael Jordan

Stability is a central property in learning and statistics promising the output of an algorithm $A$ does not change substantially when applied to similar datasets $S$ and $S'$. It is an elementary fact that any sufficiently stable algorithm…

Machine Learning · Computer Science 2025-02-13 Max Hopkins , Shay Moran