{"690768":{"#nid":"690768","#data":{"type":"event","title":"PhD Defense by Qing Ye","body":[{"value":"\u003Cdiv\u003E\u003Cp\u003EQing Ye\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EPh.D. Candidate in Operations Research\u003Cbr\u003EH. Milton Stewart School of Industrial and Systems Engineering\u003Cbr\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EAdvisor\/chairperson:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Christos Alexopoulos, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Weijun Xie, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003ECommittee members:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Christos Alexopoulos, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Weijun Xie, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. David Goldsman, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Edwin Romeijn, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDr. Grani A. Hanasusanto, Department of Industrial \u0026amp; Enterprise Systems Engineering, University of Illinois Urbana-Champaign\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThesis Title: Theory and Algorithms for Nonconvex Learning and Optimization\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDate:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EMonday, June 22nd, 2026\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003ETime:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E1:00 PM \u2013 2:00 PM EDT\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EZoom Link:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/nam12.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fgatech.zoom.us%2Fj%2F98113715264\u0026amp;data=05%7C02%7Cfkhan47%40gatech.edu%7Cfb0ed75c290745054f6f08decbaf244e%7C482198bbae7b4b258b7a6d7f32faa083%7C1%7C0%7C639172150257781087%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=OEGjuiPI%2F7wdG7WW1urm6LhitJ4d%2BZlUrFXkr%2FhnGY8%3D\u0026amp;reserved=0\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022 title=\u0022Original URL: https:\/\/gatech.zoom.us\/j\/98113715264. Click or tap if you trust this link.\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/98113715264\u003C\/a\u003E\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThis dissertation contributes to the field of mathematical programming on three fronts by developing: (i) a mixed-integer programming framework for fair classification; (ii) distributionally fair stochastic programming methods based on a Wasserstein fairness measure; and (iii) second-order conic and polyhedral approximations of the exponential cone.\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EFirst, we propose a unified mixed-integer optimization framework for fair classification. Unlike surrogate-based approaches, the framework models discrete group fairness measures exactly while jointly optimizing prediction accuracy and regularization. It applies to support vector machines, logistic regression, neural networks, and multiclass models. For support vector machines, we derive an exact mixed-integer conic formulation, establish Fisher consistency, and show that fairness enforcement can be interpreted as unbiased subdata selection. This structure leads to an iterative reselection algorithm with convergence and approximation guarantees. Computational results show that exact fairness modeling yields competitive fairness\u2013accuracy trade-offs and demonstrates the practical scalability of mixed-integer optimization for fair machine learning.\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003ESecond, we introduce Distributionally Fair Stochastic Optimization (DFSO), which uses Wasserstein distance to reduce disparities between group utility distributions while allowing a controlled level of inefficiency. We show that the epigraph of the Wasserstein fairness measure admits a mixed-integer convex representation and derive Jensen and Gelbrich lower bounds. We prove tightness properties of the Gelbrich bound and characterize its gap from the Wasserstein fairness measure. These results motivate efficient algorithms whose computational performance is validated on socially relevant stochastic optimization problems.\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EFinally, we study mixed-integer exponential conic programs arising from models with exponential and logarithmic terms, including logistic regression and entropy optimization. To leverage existing MILP and MISOCP technology, we develop SOC and polyhedral approximation schemes for the exponential cone, establish explicit error and lower-bound guarantees, and implement these approximations within scalable computational frameworks. Numerical experiments show substantial improvements over state-of-the-art exponential cone solvers.\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ETheory and Algorithms for Nonconvex Learning and Optimization\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Theory and Algorithms for Nonconvex Learning and Optimization"}],"uid":"36872","created_gmt":"2026-06-16 17:40:04","changed_gmt":"2026-06-16 17:41:52","author":"fkhan47","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-06-22T13:00:29-04:00","event_time_end":"2026-06-22T14:00:29-04:00","event_time_end_last":"2026-06-22T14:00:29-04:00","gmt_time_start":"2026-06-22 17:00:29","gmt_time_end":"2026-06-22 18:00:29","gmt_time_end_last":"2026-06-22 18:00:29","rrule":null,"timezone":"America\/New_York"},"extras":[],"related_links":[{"url":"https:\/\/nam12.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fgatech.zoom.us%2Fj%2F98113715264\u0026data=05%7C02%7Cfkhan47%40gatech.edu%7Cfb0ed75c290745054f6f08decbaf244e%7C482198bbae7b4b258b7a6d7f32faa083%7C1%7C0%7C639172150257781087%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026sdata=OEGjuiPI%2F7wdG7WW1urm6LhitJ4d%2BZlUrFXkr%2FhnGY8%3D\u0026reserved=0","title":"Zoom Link"}],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}