{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:42:36Z","timestamp":1787028156183,"version":"3.56.0"},"reference-count":81,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS1927486"],"award-info":[{"award-number":["IIS1927486"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS1850023"],"award-info":[{"award-number":["IIS1850023"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS2046381"],"award-info":[{"award-number":["IIS2046381"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["60NANB18D227"],"award-info":[{"award-number":["60NANB18D227"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1453432"],"award-info":[{"award-number":["CCF-1453432"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000161","name":"U.S. Department of Commerce, National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["IIS1927486"],"award-info":[{"award-number":["IIS1927486"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000161","name":"U.S. Department of Commerce, National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["IIS1850023"],"award-info":[{"award-number":["IIS1850023"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000161","name":"U.S. Department of Commerce, National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["IIS2046381"],"award-info":[{"award-number":["IIS2046381"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000161","name":"U.S. Department of Commerce, National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["60NANB18D227"],"award-info":[{"award-number":["60NANB18D227"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000161","name":"U.S. Department of Commerce, National Institute of Standards and Technology","doi-asserted-by":"publisher","award":["CCF-1453432"],"award-info":[{"award-number":["CCF-1453432"]}],"id":[{"id":"10.13039\/100000161","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US NSF","doi-asserted-by":"publisher","award":["IIS1927486"],"award-info":[{"award-number":["IIS1927486"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US NSF","doi-asserted-by":"publisher","award":["IIS1850023"],"award-info":[{"award-number":["IIS1850023"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US NSF","doi-asserted-by":"publisher","award":["IIS2046381"],"award-info":[{"award-number":["IIS2046381"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US NSF","doi-asserted-by":"publisher","award":["60NANB18D227"],"award-info":[{"award-number":["60NANB18D227"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US NSF","doi-asserted-by":"publisher","award":["CCF-1453432"],"award-info":[{"award-number":["CCF-1453432"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens from the legal, social science, and humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. Our theoretical results show that our criteria meaningfully operationalize AI fairness in terms of real-world harms, making the measurements interpretable in a manner analogous to differential privacy. We provide a simple learning algorithm using deterministic gradient methods, which respects our intersectional fairness criteria. The measurement of fairness becomes statistically challenging in the minibatch setting due to data sparsity, which increases rapidly in the number of protected attributes and in the values per protected attribute. To address this, we further develop a practical learning algorithm using stochastic gradient methods which incorporates stochastic estimation of the intersectional fairness criteria on minibatches to scale up to big data. Case studies on census data, the COMPAS criminal recidivism dataset, the HHP hospitalization data, and a loan application dataset from HMDA demonstrate the utility of our methods.<\/jats:p>","DOI":"10.3390\/e25040660","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T02:26:02Z","timestamp":1681698362000},"page":"660","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Differential Fairness: An Intersectional Framework for Fair AI"],"prefix":"10.3390","volume":"25","author":[{"given":"Rashidul","family":"Islam","sequence":"first","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamrun Naher","family":"Keya","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shimei","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6123-5282","authenticated-orcid":false,"given":"Anand D.","family":"Sarwate","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers, The State University of New Jersey, New Brunswick, NJ 08854, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James R.","family":"Foulds","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Maryland, Baltimore County, Baltimore, MD 21250, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"ref_1","first-page":"671","article-title":"Big data\u2019s disparate impact","volume":"104","author":"Barocas","year":"2016","journal-title":"Calif. Law Rev."},{"key":"ref_2","unstructured":"Munoz, C., Smith, M., and Patil, D. (2016). Big Data: A Report on Algorithmic Systems, Opportunity, and Civil Rights."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Noble, S. (2018). Algorithms of Oppression: How Search Engines Reinforce Racism, NYU Press.","DOI":"10.2307\/j.ctt1pwt9w5"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Angwin, J., Larson, J., Mattu, S., and Kirchner, L. (2023, April 04). Machine bias: There\u2019s software used across the country to predict future criminals. and it\u2019s biased against blacks. Available online: https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing.","DOI":"10.1201\/9781003278290-37"},{"key":"ref_5","unstructured":"Buolamwini, J., and Gebru, T. (2018, January 23\u201324). Gender shades: Intersectional accuracy disparities in commercial gender classification. Proceedings of the Conference on Fairness, Accountability, and Transparency, New York, NY, USA."},{"key":"ref_6","unstructured":"Bolukbasi, T., Chang, K.W., Zou, J., Saligrama, V., and Kalai, A. (2016, January 5\u201310). Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. Proceedings of the Advances in NeurIPS, Barcelona, Spain."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R. (2012, January 8\u201310). Fairness through awareness. Proceedings of the Innovations in Theoretical Computer Science (ITCS), Cambridge, MA USA.","DOI":"10.1145\/2090236.2090255"},{"key":"ref_8","unstructured":"Hardt, M., Price, E., and Srebro, N. (2016, January 5\u201310). Equality of opportunity in supervised learning. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Barcelona, Spain."},{"key":"ref_9","unstructured":"Berk, R., Heidari, H., Jabbari, S., Joseph, M., Kearns, M., Morgenstern, J., Neel, S., and Roth, A. (2017, January 14). A convex framework for fair regression. Proceedings of the FAT\/ML Workshop, Halifax, NS, Canada."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, T., Yatskar, M., Ordonez, V., and Chang, K.W. (2017, January 9\u201311). Men also like shopping: Reducing gender bias amplification using corpus-level constraints. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark.","DOI":"10.18653\/v1\/D17-1323"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Islam, R., Keya, K., Zeng, Z., Pan, S., and Foulds, J. (2021, January 19\u201323). Debiasing Career Recommendations with Neural Fair Collaborative Filtering. Proceedings of the Web Conference, Ljubljana, Slovenia.","DOI":"10.1145\/3442381.3449904"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Keya, K.N., Islam, R., Pan, S., Stockwell, I., and Foulds, J.R. (May, January 29). Equitable Allocation of Healthcare Resources with Fair Survival Models. Proceedings of the 2021 SIAM International Conference on Data Mining (SIAM), Virtual.","DOI":"10.1137\/1.9781611976700.22"},{"key":"ref_13","unstructured":"Campolo, A., Sanfilippo, M., Whittaker, M., Crawford, A.S.K., and Barocas, S. (2017). AI Now 2017 Symposium Report, AI Now."},{"key":"ref_14","unstructured":"Mitchell, S., Potash, E., and Barocas, S. (2018). Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Keyes, O., Hutson, J., and Durbin, M. (2019, January 4\u20139). A Mulching Proposal: Analysing and Improving an Algorithmic System for Turning the Elderly into High-Nutrient Slurry. Proceedings of the Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems, Glasgow, UK.","DOI":"10.1145\/3290607.3310433"},{"key":"ref_16","first-page":"139","article-title":"Demarginalizing the intersection of race and sex: A black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics","volume":"1989","author":"Crenshaw","year":"1989","journal-title":"Univ. Chic. Leg. Forum"},{"key":"ref_17","unstructured":"Kearns, M., Neel, S., Roth, A., and Wu, Z. (2018, January 10\u201315). Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_18","unstructured":"Hebert-Johnson, U., Kim, M., Reingold, O., and Rothblum, G. (2018, January 10\u201315). Multicalibration: Calibration for the (Computationally-Identifiable) Masses. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Dwork, C., McSherry, F., Nissim, K., and Smith, A. (2006, January 4\u20137). Calibrating noise to sensitivity in private data analysis. Proceedings of the Third Theory of Cryptography, New York, NY, USA.","DOI":"10.1007\/11681878_14"},{"key":"ref_20","first-page":"211","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2013","journal-title":"Theor. Comput. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mironov, I. (2017, January 21\u201325). R\u00e9nyi differential privacy. Proceedings of the 2017 IEEE 30th Computer Security Foundations symposium (CSF), Santa Barbara, CA, USA.","DOI":"10.1109\/CSF.2017.11"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Selbst, A.D., Boyd, D., Friedler, S.A., Venkatasubramanian, S., and Vertesi, J. (2019, January 29\u201331). Fairness and abstraction in sociotechnical systems. Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, USA.","DOI":"10.1145\/3287560.3287598"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jacobs, A.Z., and Wallach, H. (2021, January 3\u201310). Measurement and Fairness. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Virtual Event.","DOI":"10.1145\/3442188.3445901"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cheng, H.F., Wang, R., Zhang, Z., O\u2019Connell, F., Gray, T., Harper, F.M., and Zhu, H. (2019, January 4\u20139). Explaining decision-making algorithms through UI: Strategies to help non-expert stakeholders. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, Glasgow, UK.","DOI":"10.1145\/3290605.3300789"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Van Berkel, N., Goncalves, J., Russo, D., Hosio, S., and Skov, M.B. (2021, January 8\u201313). Effect of information presentation on fairness perceptions of machine learning predictors. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan.","DOI":"10.1145\/3411764.3445365"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, R., Harper, F.M., and Zhu, H. (2020, January 25\u201330). Factors influencing perceived fairness in algorithmic decision-making: Algorithm outcomes, development procedures, and individual differences. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA.","DOI":"10.1145\/3313831.3376813"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/2514689","article-title":"Pufferfish: A framework for mathematical privacy definitions","volume":"39","author":"Kifer","year":"2014","journal-title":"TODS"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3479562","article-title":"Algorithmic risk assessments can alter human decision-making processes in high-stakes government contexts","volume":"5","author":"Green","year":"2021","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105681","DOI":"10.1016\/j.clsr.2022.105681","article-title":"The flaws of policies requiring human oversight of government algorithms","volume":"45","author":"Green","year":"2022","journal-title":"Comput. Law Secur. Rev."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kong, Y. (2022, January 21\u201324). Are \u201cIntersectionally Fair\u201d AI Algorithms Really Fair to Women of Color? A Philosophical Analysis. Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea.","DOI":"10.1145\/3531146.3533114"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Foulds, J.R., Islam, R., Keya, K.N., and Pan, S. (2020, January 20\u201324). An intersectional definition of fairness. Proceedings of the 2020 IEEE 36th International Conference on Data Engineering (ICDE), Dallas, TX, USA.","DOI":"10.1109\/ICDE48307.2020.00203"},{"key":"ref_32","first-page":"51","article-title":"Are Parity-Based Notions of AI Fairness Desirable?","volume":"43","author":"Foulds","year":"2020","journal-title":"Bull. IEEE Tech. Comm. Data Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"453","DOI":"10.3102\/0002831217740221","article-title":"Gender equity in college majors: Looking beyond the STEM\/Non-STEM dichotomy for answers regarding female participation","volume":"55","author":"Ganley","year":"2018","journal-title":"Am. Educ. Res. J."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4","DOI":"10.2307\/2934966","article-title":"Passing for white, passing for black","volume":"58","author":"Piper","year":"1992","journal-title":"Transition"},{"key":"ref_35","unstructured":"Truth, S. (1851). Speech delivered at Women\u2019s Rights Convention."},{"key":"ref_36","unstructured":"Collins, P.H. (2002). Black Feminist thought: Knowledge, Consciousness, and the Politics of Empowerment, Routledge."},{"key":"ref_37","unstructured":"Eisenstein, Z. (1978). Capitalist Patriarchy and the Case for Socialist Feminism, Monthly Review Press."},{"key":"ref_38","unstructured":"Hooks, B. (1981). Ain\u2019t I a Woman: Black Women and Feminism, South End Press."},{"key":"ref_39","unstructured":"Lorde, A. (1984). Sister Outsider, Ten Speed Press."},{"key":"ref_40","unstructured":"Yang, F., Cisse, M., and Koyejo, O.O. (2020, January 6\u201312). Fairness with Overlapping Groups; a Probabilistic Perspective. Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual."},{"key":"ref_41","unstructured":"La Cava, W., Lett, E., and Wan, G. (2022). Proportional Multicalibration. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Lett, E., and La Cava, W. (2023). Translating Intersectionality to Fair Machine Learning in Health Sciences. SocArXiv.","DOI":"10.31235\/osf.io\/gu7yh"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1214\/17-AOAS1058","article-title":"The problem of infra-marginality in outcome tests for discrimination","volume":"11","author":"Simoiu","year":"2017","journal-title":"Ann. Appl. Stat."},{"key":"ref_44","unstructured":"Davis, A. (2011). Seven Stories Press."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1002\/yd.51","article-title":"Defining and redirecting a school-to-prison pipeline","volume":"2003","author":"Wald","year":"2003","journal-title":"New Dir. Youth Dev."},{"key":"ref_46","unstructured":"Verschelden, C. (2017). Bandwidth Recovery: Helping Students Reclaim Cognitive Resources Lost to Poverty, Racism, and Social Marginalization, Stylus."},{"key":"ref_47","unstructured":"Alexander, M. (2012). The New Jim Crow: Mass Incarceration in the Age of Colorblindness, T. N. P."},{"key":"ref_48","unstructured":"Grant, J., Mottet, L., Tanis, J., Harrison, J., Herman, J., and Keisling, M. (2011). Injustice at Every Turn: A Report of the National Transgender Discrimination Survey, National Center for Transgender Equality."},{"key":"ref_49","first-page":"28","article-title":"Fairness in Criminal Justice Risk Assessments: The State of the Art","volume":"1050","author":"Berk","year":"2018","journal-title":"Sociol. Methods Res."},{"key":"ref_50","unstructured":"Dastin, J. (2018). Amazon Scraps Secret AI Recruiting Tool That Showed Bias against Women. Reuters, Available online: https:\/\/www.reuters.com\/article\/us-amazon-com-jobs-automation-insight\/amazon-scraps-secret-ai-recruiting-tool-that-showed-bias-against-women-idUSKCN1MK08G."},{"key":"ref_51","unstructured":"Equal Employment Opportunity Commission (1978). Guidelines on Employee Selection Procedures, C.F.R. 29.1607."},{"key":"ref_52","unstructured":"Pleiss, G., Raghavan, M., Wu, F., Kleinberg, J., and Weinberger, K. (2017, January 4\u20139). On fairness and calibration. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_53","unstructured":"Donini, M., Oneto, L., Ben-David, S., Shawe-Taylor, J.S., and Pontil, M. (2018, January 3\u20138). Empirical risk minimization under fairness constraints. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_54","unstructured":"Kusner, M., Loftus, J., Russell, C., and Silva, R. (2017, January 4\u20139). Counterfactual fairness. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_55","unstructured":"Jagielski, M., Kearns, M., Mao, J., Oprea, A., Roth, A., Sharifi-Malvajerdi, S., and Ullman, J. (2018). Differentially private fair learning. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Foulds, J., Islam, R., Keya, K.N., and Pan, S. (2020, January 5\u20139). Bayesian Modeling of Intersectional Fairness: The Variance of Bias. Proceedings of the 2020 SIAM International Conference on Data Mining, Cincinnati, OH, USA.","DOI":"10.1137\/1.9781611976236.48"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1136\/bmj.292.6524.879","article-title":"Comparison of treatment of renal calculi by open surgery, percutaneous nephrolithotomy, and extracorporeal shockwave lithotripsy","volume":"292","author":"Charig","year":"1986","journal-title":"Br. Med. J."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1136\/bmj.309.6967.1480","article-title":"Confounding and Simpson\u2019s paradox","volume":"309","author":"Julious","year":"1994","journal-title":"Br. Med. J."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1126\/science.187.4175.398","article-title":"Sex Bias in Graduate Admissions: Data from Berkeley: Measuring bias is harder than is usually assumed, and the evidence is sometimes contrary to expectation","volume":"187","author":"Bickel","year":"1975","journal-title":"Science"},{"key":"ref_60","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_62","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, January 4\u20139). Automatic differentiation in pytorch. Proceedings of the Advances in Neural Information Processing Systems (Autodiff Workshop), Long Beach, CA, USA."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1111\/j.1467-9868.2009.00698.x","article-title":"On-line expectation\u2013maximization algorithm for latent data models","volume":"71","author":"Moulines","year":"2009","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"ref_64","unstructured":"Hoffman, M., Bach, F.R., and Blei, D.M. (2010, January 6\u20139). Online learning for latent Dirichlet allocation. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_65","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref_66","unstructured":"Mimno, D., Hoffman, M.D., and Blei, D.M. (July, January 26). Sparse stochastic inference for latent Dirichlet allocation. Proceedings of the 29th International Conference on Machine Learning, Edinburgh, Scotland."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Foulds, J., Boyles, L., DuBois, C., Smyth, P., and Welling, M. (2013, January 11\u201314). Stochastic collapsed variational Bayesian inference for latent Dirichlet allocation. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA.","DOI":"10.1145\/2487575.2487697"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Islam, R., and Foulds, J. (2019, January 2\u20137). Scalable Collapsed Inference for High-Dimensional Topic Models. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA.","DOI":"10.18653\/v1\/N19-1291"},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"Robbins","year":"1951","journal-title":"Ann. Math. Statist."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1137\/S0363012902417267","article-title":"Stability of stochastic approximation under verifiable conditions","volume":"44","author":"Andrieu","year":"2005","journal-title":"SIAM J. Control Optim."},{"key":"ref_71","unstructured":"Bao, M., Zhou, A., Zottola, S., Brubach, B., Desmarais, S., Horowitz, A., Lum, K., and Venkatasubramanian, S. (2021, January 6\u201314). It\u2019s COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021), Virtual."},{"key":"ref_72","unstructured":"Dua, D., and Graff, C. (2017). UCI Machine Learning Repository, University of California, School of Information and Computer Science. Available online: http:\/\/archive.ics.uci.edu\/ml."},{"key":"ref_73","unstructured":"Song, J., Kalluri, P., Grover, A., Zhao, S., and Ermon, S. (2019, January 16\u201318). Learning controllable fair representations. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan."},{"key":"ref_74","unstructured":"(2023, April 10). ProPublica\/Investigative Reporters and Editors. Home Mortgage Disclosure Act, Available online: https:\/\/www.consumerfinance.gov\/data-research\/hmda\/."},{"key":"ref_75","unstructured":"Zafar, M., Valera, I., Rodriguez, M., and Gummadi, K. (2017, January 20\u201322). Fairness constraints: Mechanisms for fair classification. Proceedings of the AISTATS, Lauderdale, FL, USA."},{"key":"ref_76","first-page":"8026","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref_77","first-page":"209","article-title":"Methods of measuring the concentration of wealth","volume":"9","author":"Lorenz","year":"1905","journal-title":"Publ. Am. Stat. Assoc."},{"key":"ref_78","unstructured":"Agarwal, A., Beygelzimer, A., Dud\u00edk, M., Langford, J., and Wallach, H. (2018, January 10\u201315). A reductions approach to fair classification. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_79","doi-asserted-by":"crossref","unstructured":"Fioretto, F., Van Hentenryck, P., Mak, T.W., Tran, C., Baldo, F., and Lombardi, M. (2020, January 14\u201318). Lagrangian Duality for Constrained Deep Learning. Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2020, Ghent, Belgium.","DOI":"10.1007\/978-3-030-67670-4_8"},{"key":"ref_80","doi-asserted-by":"crossref","unstructured":"Tran, C., Fioretto, F., and Van Hentenryck, P. (2021, January 2\u20139). Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i11.17193"},{"key":"ref_81","unstructured":"Foulds, J.R., and Pan, S. (2020). Bulletin of the IEEE Technical Committee on Data Engineering, IEEE Computer Society."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/4\/660\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:16:14Z","timestamp":1760123774000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/4\/660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,14]]},"references-count":81,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["e25040660"],"URL":"https:\/\/doi.org\/10.3390\/e25040660","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,14]]}}}