4 papers
No-Regret and Incentive-Compatible Online Learning
Rupert Freeman, David M. Pennock, Chara Podimata +1
We study online learning settings in which experts act strategically to maximize their influence on the learning algorithm's predictions by potentially misreporting their beliefs a…
Learning Strategy-Aware Linear Classifiers
Yiling Chen, Yang Liu, Chara Podimata
We address the question of repeatedly learning linear classifiers against agents who are strategically trying to game the deployed classifiers, and we use the Stackelberg regret to…
A Bridge between Liquid and Social Welfare in Combinatorial Auctions with Submodular Bidders
Dimitris Fotakis, Kyriakos Lotidis, Chara Podimata
We study incentive compatible mechanisms for Combinatorial Auctions where the bidders have submodular (or XOS) valuations and are budget-constrained. Our objective is to maximize t…
Strategyproof Linear Regression in High Dimensions
Yiling Chen, Chara Podimata, Ariel D. Procaccia +1
This paper is part of an emerging line of work at the intersection of machine learning and mechanism design, which aims to avoid noise in training data by correctly aligning the in…