Strategyproof Linear Regression in High Dimensions

Chen, Yi‐Ling; Podimata, Chara; Procaccia, Ariel D.; Shah, Nisarg

doi:10.1145/3219166.3219175

Cited by 65 publications

(45 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our paper is related to an emerging line of work at the intersection of machine learning and algorithmic game theory, dealing with scenarios where the samples used for training learning algorithms are controlled by strategic agents, who aim to optimize their personal benefit. Indicatively, there has been recent interest in the analysis of the effect of strategic behavior on the efficiency of existing algorithms, as well as the design of algorithms resilient to strategic manipulation for linear regression (Ben-Porat & Tennenholtz, 2019;Chen et al, 2018;Dekel et al, 2010;Hossain & Shah, 2020;Perote & Perote-Peña, 2004;Waggoner et al, 2015) and classification (Chen et al, 2019;Dong et al, 2018;Meir et al, 2012;Zhang et al, 2019).…”

Section: Other Related Workmentioning

confidence: 99%

Optimally Deceiving a Learning Leader in Stackelberg Games

BirmpasGeorgios

GanJiarui

Hollender

et al. 2021

jair

View full text Add to dashboard Cite

Recent results have shown that algorithms for learning the optimal commitment in a Stackelberg game are susceptible to manipulation by the follower. These learning algorithms operate by querying the best responses of the follower, who consequently can deceive the algorithm by using fake best responses, typically by responding according to fake payoffs that are different from the actual ones. For this strategic behavior to be successful, the main challenge faced by the follower is to pinpoint the fake payoffs that would make the learning algorithm output a commitment that benefits them the most. While this problem has been considered before, the related literature has only focused on a simple setting where the follower can only choose from a finite set of payoff matrices, thus leaving the general version of the problem unanswered. In this paper, we fill this gap by showing that it is always possible for the follower to efficiently compute (near-)optimal fake payoffs, for various scenarios of learning interaction between the leader and the follower. Our results also establish an interesting connection between the follower’s deception and the leader’s maximin utility: through deception, the follower can induce almost any (fake) Stackelberg equilibrium if and only if the leader obtains at least their maximin utility in this equilibrium.

show abstract

Section: Other Related Workmentioning

confidence: 99%

Optimally Deceiving a Learning Leader in Stackelberg Games

BirmpasGeorgios

GanJiarui

Hollender

et al. 2021

jair

View full text Add to dashboard Cite

show abstract

“…Our work is additionally related to the recent work on incentive compatible machine learning [24,7,4]. In these settings, the "social choice" being made is a machine learning predictor where agents benefit from their point having small error with respect to the chosen predictor.…”

Section: Additional Related Workmentioning

confidence: 99%

Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences

Schoenebeck

Tao

2021

Preprint

View full text Add to dashboard Cite

We consider two-alternative elections where voters' preferences depend on a state variable that is not directly observable. Each voter receives a private signal that is correlated to the state variable. Voters may be "contingent" with different preferences in different states; or predetermined with the same preference in every state. In this setting, even if every voter is a contingent voter, agents voting according to their private information need not result in the adoption of the universally preferred alternative, because the signals can be systematically biased.We present an easy-to-deploy mechanism that elicits and aggregates the private signals from the voters, and outputs the alternative that is favored by the majority. In particular, voters truthfully reporting their signals forms a strong Bayes Nash equilibrium (where no coalition of voters can deviate and receive a better outcome).

show abstract

“…There is also work on strategyproof linear regression [7,10,13]. The setup of these models is also quite different from ours -typically, the strategic agents submit (x, y) pairs where x is fixed and y can be chosen strategically, and the evaluator's goal is to perform linear regression in a way that incentivizes truthful reporting of y.…”

Section: Evaluator's Decision Rulementioning

confidence: 99%

“…Thus, (8) is equivalent to (4), which has value κ j = 1 by assumption. By duality, (7) also has value κ j = 1, meaning L j is non-empty.…”

Section: Incentivizing Particular Effort Profilesmentioning

confidence: 99%

How Do Classifiers Induce Agents to Invest Effort Strategically?

Kleinberg

Raghavan

2019

Proceedings of the 2019 ACM Conference on Economics and Computation

View full text Add to dashboard Cite

Algorithms are often used to produce decision-making rules that classify or evaluate individuals. When these individuals have incentives to be classified a certain way, they may behave strategically to influence their outcomes. We develop a model for how strategic agents can invest effort in order to change the outcomes they receive, and we give a tight characterization of when such agents can be incentivized to invest specified forms of effort into improving their outcomes as opposed to "gaming" the classifier. We show that whenever any "reasonable" mechanism can do so, a simple linear mechanism suffices.

show abstract

Strategyproof Linear Regression in High Dimensions

Cited by 65 publications

References 39 publications

Optimally Deceiving a Learning Leader in Stackelberg Games

Optimally Deceiving a Learning Leader in Stackelberg Games

Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences

How Do Classifiers Induce Agents to Invest Effort Strategically?

Contact Info

Product

Resources

About