國立虎尾科技大學 |

Scalable Optimization for Trustworthy AI : = Robust and Fair Machine Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Scalable Optimization for Trustworthy AI :/
其他題名:	Robust and Fair Machine Learning.
作者:	Baharlouei, Sina.
面頁冊數:	1 online resource (347 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798382651774

Scalable Optimization for Trustworthy AI : = Robust and Fair Machine Learning.
Baharlouei, Sina.

Scalable Optimization for Trustworthy AI :Robust and Fair Machine Learning. - 1 online resource (347 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Thesis (Ph.D.)--University of Southern California, 2024.

Includes bibliographical references

The advent of artificial intelligence (AI) has revolutionized a diverse set of complex decision-making tasks in society and industry. Empirical Risk Minimization (ERM), as the dominant paradigm for training and deploying large-scale AI models, has showcased remarkable efficacy across diverse applications such as object detection, language model learning, and speech recognition. Despite its promising results, ERM grapples with notable limitations that curtail its suitability for critical decision-making tasks. One significant drawback lies in the potential for ERM-based training to yield unfair outcomes, particularly with respect to protected groups such as racial minorities and women. Additionally, the robustness of these models hinges heavily on the assumption that the training data adheres to the assumption of being independent and identically distributed (IID) samples of the eventual test (production) data. However, this assumption may be compromised if there are disparities between the distribution of the target domain and the source domain, stemming from factors such as changes in environment, geographical location, or date. Furthermore, challenges such as batch effects, missing values, and the influence of adversarial agents serve to disrupt the IID assumption, rendering conventional ERM training unreliable and leading to significant performance degradation in such scenarios.In this thesis, we study optimization methods and algorithms for robust and fair training of machine-learning models. We study the robustness of machine learning models in different scenarios, including:1. Robust Imputation and Inference in the Presence of Missing Values (Chapter 2)2. Learning Robust Models in the Presence of Batch Effects (Chapter 3)3. Robustness Against Adversarial Attacks (Chapter 4)4. Robustness Against Distributional Changes (Chapter 7 and Chapter 8) for Fair Empirical Risk MinimizationIn Section Two (Chapter 5 and Chapter 6), our focus shifts to developing scalable algorithms to enhance fairness criteria within machine-learning models. Our approach involves introducing innovative measures and methodologies designed to integrate fairness constraints into the empirical risk minimization framework. In the study of fair empirical risk minimization, our primary considerations center around two pivotal aspects: evaluating the model's performance through the accuracy-fairness tradeoff and the amenability to scalable stochastic optimization algorithms. We put forth a diverse set of measures for quantifying fairness violations in empirical risk minimization tasks, delving into comprehensive analyses that showcase the convergence and performance guarantees of the optimization algorithms developed for these measures.While extensive research has delved into fortifying vanilla empirical risk minimization against distribution shifts, there is a noticeable scarcity of studies and methodologies addressing the robustness of fair empirical risk minimization models. Therefore, it is crucial to design large-scale fair algorithms that demonstrate resilience against alterations (shifts) in the data distribution. Unlike the conventional fair empirical risk minimization, we dispense with the implicit assumption that the training data constitutes an independently and identically distributed (IID) sample of the test data. In Chapter 7, we focus on learning fair models in the presence of distribution shifts. We build our distributionally robust model on the stochastic framework developed in Chapter 6. More precisely, we robustify the empirical risk minimization objective regularized by the Exponential Renyi Mutual Information (ERMI) measure against distributional changes. ERMI, as a measure of independence, is a special case of f-divergences.Finally, in Chapter 8, we propose a convergent scalable (stochastic) distributionally robust fair empirical risk minimization via f-divergences. This chapter generalizes the stochastic framework in Chapter 6. Further, it provides a novel distributionally robust optimization framework using ℓp norms as the uncertainty balls.A shared attribute among the formulations and models presented in the thesis is their incorporation of data-driven constraints or regularization into the vanilla Empirical Risk Minimization (ERM) framework, resulting in min-max optimization problems. Consequently, the methods and algorithms devised have broader applicability beyond the specific issues addressed in the thesis, extending their utility to applications such as domain generalization, contrastive learning, and meta-learning. We discuss the broader impacts of the presented algorithms and methods in the thesis and potential future directions in the Conclusion (Chapter 9).

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

Mode of access: World Wide Web

ISBN: 9798382651774Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Distributionally robustIndex Terms--Genre/Form:

554714
Electronic books.

Scalable Optimization for Trustworthy AI : = Robust and Fair Machine Learning.
LDR:06180ntm a22004097 4500 001 1147747
005 20240916065458.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382651774
035 $a (MiAaPQ)AAI31240657
035 $a AAI31240657
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Baharlouei, Sina. $3 1473553
245 1 0 $a Scalable Optimization for Trustworthy AI : $b Robust and Fair Machine Learning.
264 0 $c 2024
300 $a 1 online resource (347 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: 85-11, Section: B.
500 $a Advisor: Razaviyayn, Meisam.
502 $a Thesis (Ph.D.)--University of Southern California, 2024.
504 $a Includes bibliographical references
520 $a The advent of artificial intelligence (AI) has revolutionized a diverse set of complex decision-making tasks in society and industry. Empirical Risk Minimization (ERM), as the dominant paradigm for training and deploying large-scale AI models, has showcased remarkable efficacy across diverse applications such as object detection, language model learning, and speech recognition. Despite its promising results, ERM grapples with notable limitations that curtail its suitability for critical decision-making tasks. One significant drawback lies in the potential for ERM-based training to yield unfair outcomes, particularly with respect to protected groups such as racial minorities and women. Additionally, the robustness of these models hinges heavily on the assumption that the training data adheres to the assumption of being independent and identically distributed (IID) samples of the eventual test (production) data. However, this assumption may be compromised if there are disparities between the distribution of the target domain and the source domain, stemming from factors such as changes in environment, geographical location, or date. Furthermore, challenges such as batch effects, missing values, and the influence of adversarial agents serve to disrupt the IID assumption, rendering conventional ERM training unreliable and leading to significant performance degradation in such scenarios.In this thesis, we study optimization methods and algorithms for robust and fair training of machine-learning models. We study the robustness of machine learning models in different scenarios, including:1. Robust Imputation and Inference in the Presence of Missing Values (Chapter 2)2. Learning Robust Models in the Presence of Batch Effects (Chapter 3)3. Robustness Against Adversarial Attacks (Chapter 4)4. Robustness Against Distributional Changes (Chapter 7 and Chapter 8) for Fair Empirical Risk MinimizationIn Section Two (Chapter 5 and Chapter 6), our focus shifts to developing scalable algorithms to enhance fairness criteria within machine-learning models. Our approach involves introducing innovative measures and methodologies designed to integrate fairness constraints into the empirical risk minimization framework. In the study of fair empirical risk minimization, our primary considerations center around two pivotal aspects: evaluating the model's performance through the accuracy-fairness tradeoff and the amenability to scalable stochastic optimization algorithms. We put forth a diverse set of measures for quantifying fairness violations in empirical risk minimization tasks, delving into comprehensive analyses that showcase the convergence and performance guarantees of the optimization algorithms developed for these measures.While extensive research has delved into fortifying vanilla empirical risk minimization against distribution shifts, there is a noticeable scarcity of studies and methodologies addressing the robustness of fair empirical risk minimization models. Therefore, it is crucial to design large-scale fair algorithms that demonstrate resilience against alterations (shifts) in the data distribution. Unlike the conventional fair empirical risk minimization, we dispense with the implicit assumption that the training data constitutes an independently and identically distributed (IID) sample of the test data. In Chapter 7, we focus on learning fair models in the presence of distribution shifts. We build our distributionally robust model on the stochastic framework developed in Chapter 6. More precisely, we robustify the empirical risk minimization objective regularized by the Exponential Renyi Mutual Information (ERMI) measure against distributional changes. ERMI, as a measure of independence, is a special case of f-divergences.Finally, in Chapter 8, we propose a convergent scalable (stochastic) distributionally robust fair empirical risk minimization via f-divergences. This chapter generalizes the stochastic framework in Chapter 6. Further, it provides a novel distributionally robust optimization framework using ℓp norms as the uncertainty balls.A shared attribute among the formulations and models presented in the thesis is their incorporation of data-driven constraints or regularization into the vanilla Empirical Risk Minimization (ERM) framework, resulting in min-max optimization problems. Consequently, the methods and algorithms devised have broader applicability beyond the specific issues addressed in the thesis, extending their utility to applications such as domain generalization, contrastive learning, and meta-learning. We discuss the broader impacts of the presented algorithms and methods in the thesis and potential future directions in the Conclusion (Chapter 9).
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
650 4 $a Industrial engineering. $3 679492
653 $a Distributionally robust
653 $a Machine learning
653 $a Optimization algorithms
653 $a Responsible AI
653 $a Stochastic optimization
655 7 $a Electronic books. $2 local $3 554714
690 $a 0796
690 $a 0800
690 $a 0984
690 $a 0546
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Southern California. $b Industrial and Systems Engineering. $3 1187829
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31240657 $z click for full text (PQDT)