Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tübingen AI Center（蒂宾根人工智能中心）；California Institute of Technology（加州理工学院）；University of California, Berkeley（加州大学伯克利分校）
Moritz Hardt, Eric Mazumdar, Celestine Mendler-Dünner, Tijana Zrnic
备注：
Published at ICML 2023; Revision corrects epsilon-dependence in the analysis
We initiate a principled study of algorithmic collective action on digital platforms that deploy machine learning algorithms. We propose a simple theoretical model of a collective interacting with a firm's learning algorithm. The collective pools the data of participating individuals and executes an algorithmic strategy by instructing participants how to modify their own data to achieve a collective goal. We investigate the consequences of this model in three fundamental learning-theoretic settings: the case of a nonparametric optimal learning algorithm, a parametric risk minimizer, and gradient-based optimization. In each setting, we come up with coordinated algorithmic strategies and characterize natural success criteria as a function of the collective's size. Complementing our theory, we conduct systematic experiments on a skill classification task involving tens of thousands of resumes from a gig platform for freelancers. Through more than two thousand model training runs of a BERT-like language model, we see a striking correspondence emerge between our empirical observations and the predictions made by our theory. Taken together, our theory and experiments broadly support the conclusion that algorithmic collectives of exceedingly small fractional size can exert significant control over a platform's learning algorithm.
A Causal Perspective on Meaningful and Robust Algorithmic Recourse
Institute for Statistics, LMU Munich（慕尼黑大学统计研究所）；Research Group Neuroinformatics, University of Vienna（维也纳大学神经信息学研究组）；Munich Center for Mathematical Philosophy, LMU Munich（慕尼黑大学慕尼黑数学哲学中心）
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；University of Tübingen（蒂宾根大学）；University College London（伦敦大学学院）
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning Systems（马克斯·普朗克-ETH学习系统中心）；University of Cambridge（剑桥大学）；Saarland University（萨尔兰大学）
Is Thompson Sampling Susceptible to Algorithmic Collusion?
School of Information Management and Engineering, Shanghai University of Finance and Economics（上海财经大学信息管理与工程学院）；The Rotman School of Management, University of Toronto（多伦多大学罗特曼管理学院）；Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong（香港中文大学系统工程与工程管理学系）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tübingen AI Center（图宾根人工智能中心）；Department of Computer Science, University of Copenhagen（哥本哈根大学计算机科学系）；ETH Zurich（苏黎世联邦理工学院）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；Saarland University（萨尔大学）；The Alan Turing Institute（艾伦·图灵研究所）
Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
ARC Centre of Excellence for Automated Decision-Making and Society（自动化决策与社会卓越中心）；School of Computing Technologies, RMIT University（计算技术学院，拉筹纳斯大学）；Department of Computer Science, ETH Zurich（计算机科学系，苏黎世联邦理工学院）
