paper-with-me

홈 › Papers

Preference learning along multiple criteria: A game-theoretic perspective

2021-05-05 · NeurIPS 2020 12 · Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright

The literature on ranking from ordinal data is vast, and there are several ways to aggregate overall preferences from pairwise comparisons between objects. In particular, it is well known that any Nash equilibrium of the zero sum game induced by the preference matrix defines a natural solution concept (winning distribution over objects) known as a von Neumann winner. Many real-world problems, however, are inevitably multi-criteria, with different pairwise preferences governing the different criteria. In this work, we generalize the notion of a von Neumann winner to the multi-criteria setting by taking inspiration from Blackwell's approachability. Our framework allows for non-linear aggregation of preferences across criteria, and generalizes the linearization-based approach from multi-objective optimization. From a theoretical standpoint, we show that the Blackwell winner of a multi-criteria problem instance can be computed as the solution to a convex optimization problem. Furthermore, given random samples of pairwise comparisons, we show that a simple plug-in estimator achieves near-optimal minimax sample complexity. Finally, we showcase the practical utility of our framework in a user study on autonomous driving, where we find that the Blackwell winner outperforms the von Neumann winner for the overall preferences.

📄 PDF Abstract BibTeX arXiv:2105.01850

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

AI Alignment through a Game-theoretic Lens: A Survey

2026-08-28 · Yanan Cai, Zhongrui Zhao, Zhigang Lu, Ickjai Lee 외 arxiv

As large language models and increasingly capable AI agents are deployed in high-risk settings, aligning them with complex human values has become a central challenge. Existing alignment methods, while effective in impro…

Data-driven Preference Learning Methods for Sorting Problems with Multiple Temporal Criteria

2023-09-22 · Yijun Li, Mengzhuo Guo, Miłosz Kadziński, Qingpeng Zhang

The advent of predictive methodologies has catalyzed the emergence of data-driven decision support across various domains. However, developing models capable of effectively handling input time series data presents an end…

Ensemble Learning

Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning

2021-06-05 · ICLR 2022 4 · Yatao Bian, Yu Rong, Tingyang Xu, Jiaxiang Wu 외

Valuation problems, such as feature interpretation, data valuation and model valuation for ensembles, become increasingly more important in many machine learning applications. Such problems are commonly solved by well-kn…

Data ValuationVariational Inference

Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching

2025-05-27 · Zhekun Shi, Kaizhao Liu, Qi Long, Weijie J. Su 외

Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game. However, using raw preference as the pa…

Diversity

Optimal portfolio selection of many players under relative performance criteria in the market model with random coefficients

2022-08-16 · Jeong Yin Park

We study the optimal portfolio selection problem under relative performance criteria in the market model with random coefficients from the perspective of many players game theory. We consider five random coefficients whi…