國立虎尾科技大學 |

Incentive-Aware Machine Learning for Decision Making.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Incentive-Aware Machine Learning for Decision Making./
作者:	Podimata, Charikleia.
面頁冊數:	1 online resource (421 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-06, Section: B.
Contained By:	Dissertations Abstracts International84-06B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798357574572

Incentive-Aware Machine Learning for Decision Making.
Podimata, Charikleia.

Incentive-Aware Machine Learning for Decision Making. - 1 online resource (421 pages)

Source: Dissertations Abstracts International, Volume: 84-06, Section: B.

Thesis (Ph.D.)--Harvard University, 2022.

Includes bibliographical references

Machine Learning algorithms are increasingly being deployed in consequential decision-making for people's lives. These decisions affect widely different aspects of our lives; e.g., Machine Learning algorithms decide what content to serve us online (thus guiding our purchasing behavior and overall beliefs) or whether we are creditworthy enough for a loan. In light of how consequential these algorithmic decisions are, people have been documented to ``strategize'' with the data that they feed to the Machine Learning algorithms hoping to obtain better outcomes or decisions. This dissertation focuses on such decision-making settings where people are incentivized to react to the algorithmic decisions made. Incentive-aware Machine Learning for decision-making creates a new ecosystem with three key stakeholders: the institutions deploying the algorithms, the individuals who are being impacted by the algorithms, and society as a whole. It is natural to expect that oftentimes there is tension between the goals of these stakeholders. In this dissertation, we study the tension that arises from each of the stakeholders' perspectives. We start by thinking about the problem of algorithmic decision making from the institution's perspective. Drawing intuition from the literature on Algorithmic Game Theory, we build new machine learning algorithms that align the incentives of the individuals with these of the institution (incentive compatibility), while not sacrificing too much accuracy. Incentive-compatibility is the holy grail of incentive alignment and is sometimes unattainable. To alleviate this, we propose Machine Learning algorithms that learn to adapt to the incentives of the agents that they face, hence also ensuring a form of robustness. Shifting gears, we focus on the societal implications of information discrepancy regarding the deployed machine learning algorithms to different subpopulations. Finally, we study incentive-aware learning in settings where there are misspecifications regarding the behavioral model of the agents and incentive-aware learning in settings where the agents are non-myopic (and sometimes, they are even learners themselves).This dissertation presents foundational theoretical advancements that range from algorithms for ubiquitous tasks such as linear regression and classification, prediction with expert advice, and Lipschitz bandits to theoretical results tailored to specific application domains such as credit scoring, forecasting, pricing, and auctions.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798357574572Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

FairnessIndex Terms--Genre/Form:

554714
Electronic books.

Incentive-Aware Machine Learning for Decision Making.
LDR:03829ntm a22003857 4500 001 1143282
005 20240517100354.5
006 m o d
007 cr mn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798357574572
035 $a (MiAaPQ)AAI29325372
035 $a AAI29325372
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Podimata, Charikleia. $3 1467915
245 1 0 $a Incentive-Aware Machine Learning for Decision Making.
264 0 $c 2022
300 $a 1 online resource (421 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-06, Section: B.
500 $a Advisor: Chen, Yiling.
502 $a Thesis (Ph.D.)--Harvard University, 2022.
504 $a Includes bibliographical references
520 $a Machine Learning algorithms are increasingly being deployed in consequential decision-making for people's lives. These decisions affect widely different aspects of our lives; e.g., Machine Learning algorithms decide what content to serve us online (thus guiding our purchasing behavior and overall beliefs) or whether we are creditworthy enough for a loan. In light of how consequential these algorithmic decisions are, people have been documented to ``strategize'' with the data that they feed to the Machine Learning algorithms hoping to obtain better outcomes or decisions. This dissertation focuses on such decision-making settings where people are incentivized to react to the algorithmic decisions made. Incentive-aware Machine Learning for decision-making creates a new ecosystem with three key stakeholders: the institutions deploying the algorithms, the individuals who are being impacted by the algorithms, and society as a whole. It is natural to expect that oftentimes there is tension between the goals of these stakeholders. In this dissertation, we study the tension that arises from each of the stakeholders' perspectives. We start by thinking about the problem of algorithmic decision making from the institution's perspective. Drawing intuition from the literature on Algorithmic Game Theory, we build new machine learning algorithms that align the incentives of the individuals with these of the institution (incentive compatibility), while not sacrificing too much accuracy. Incentive-compatibility is the holy grail of incentive alignment and is sometimes unattainable. To alleviate this, we propose Machine Learning algorithms that learn to adapt to the incentives of the agents that they face, hence also ensuring a form of robustness. Shifting gears, we focus on the societal implications of information discrepancy regarding the deployed machine learning algorithms to different subpopulations. Finally, we study incentive-aware learning in settings where there are misspecifications regarding the behavioral model of the agents and incentive-aware learning in settings where the agents are non-myopic (and sometimes, they are even learners themselves).This dissertation presents foundational theoretical advancements that range from algorithms for ubiquitous tasks such as linear regression and classification, prediction with expert advice, and Lipschitz bandits to theoretical results tailored to specific application domains such as credit scoring, forecasting, pricing, and auctions.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Fairness
653 $a Incentives
653 $a Online decision making
653 $a Strategic agents
653 $a Strategyproof ML
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0501
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Harvard University. $b Engineering and Applied Sciences - Computer Science. $3 1467916
773 0 $t Dissertations Abstracts International $g 84-06B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29325372 $z click for full text (PQDT)