{"690385":{"#nid":"690385","#data":{"type":"news","title":"Ph.D. Graduate Q\u0026A:\u202fXinyuan Cao","body":[{"value":"\u003Cdiv\u003E\u003Cp\u003EAs a machine learning (ML) theorist, Xinyuan\u003Cstrong\u003E \u003C\/strong\u003ECao spent her Ph.D. at Georgia Tech digging into the mathematical foundations of\u202fartificial intelligence (AI).\u202f\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003ECao\u0027s work has earned her recognition, including the 2024 J.P. Morgan AI Research Ph.D. Fellowship and the 2023 \u003Ca href=\u0022https:\/\/arc.gatech.edu\/student-fellowships\/\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003EGeorgia Tech ARC Fellowship\u003C\/a\u003E. Last week,\u202fshe joined the Class of 2026 as she received her\u202fPh.D. in machine learning.\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EBefore starting her\u202fnext role in AI research, Cao\u202fshared the ideas and people that defined her time at Tech.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhat did your research focus on?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EI work on\u202fML\u202ftheory, which\u202ffocuses on building foundations for ML algorithms.\u202fWe\u202ftry to understand why certain\u202falgorithms work or don\u2019t work from a theoretical perspective.\u202fThis ensures a better underlying understanding of those\u202falgorithms.\u202f\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhat made you interested in studying that topic?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EWhen I was starting my Ph.D.,\u202fa lot of new AI and ML\u202ftechnologies were coming\u202fout\u202f, and I was really interested in\u202funderstanding them.\u202fI feel it\u2019s\u202fmeaningful\u202ffor us to step back and think about more foundational things.\u202fI also like that the research involves a lot of theory that comes from geometry or algebra.\u202fSome of these theories could be from 100 years ago, but you can use\u202fthem\u202fto show an algorithm that was just proposed this year.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhy did you choose to study at Georgia Tech?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EWhen I talked to\u202fprofessors\u202fhere,\u202fwe found many common interests\u202fin the field of\u202fmachine learning theory, and that was very exciting.\u202fGeorgia Tech\u2019s CS rankings and the great weather here were also big factors.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EAre there any specific people who helped you during your Ph.D. journey?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EDefinitely my\u202fadvisor,\u202f\u003Ca href=\u0022https:\/\/faculty.cc.gatech.edu\/~vempala\/\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003ESantosh Vempala\u003C\/a\u003E. We\u2019re working\u202fin an area that is a combination of very traditional theory and modern\u202ftechnologies,\u202fand this makes it hard to define\u202fa clear question to focus on.\u202fSantosh has been very helpful\u202fthroughout that experience, and working together has been really nice.\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EI\u2019ve also\u202fworked with\u202f\u003Ca href=\u0022https:\/\/faculty.cc.gatech.edu\/~jabernethy9\/\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003EJacob\u202fAbernethy\u003C\/a\u003E\u202fand appreciate\u202flearning from him. He has an ML theory reading group that I\u2019ve attended\u202ffrequently, and that\u2019s a good memory for me.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhat advice would you give someone interested in pursuing a Ph.D.?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EI think it\u2019s important to find the problem that you are truly interested in.\u202fIn research, you may reach a point where neither you nor your advisor knows how to proceed, and it is unclear whether the problem is even solvable.\u202fIf you\u2019re not working on something that you really care about, it can be hard to\u202fpush through and find the motivation to keep working on it and solve it.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhat are your plans after graduation?\u202f\u003C\/strong\u003E\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EI have accepted a postdoctoral fellowship at the Vector Institute, where I will continue my AI research.\u202f\u202f\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ERecent Ph.D. graduate in machine learning Xinyuan Cao discusses her experience at Georgia Tech.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Q\u0026A with Ph.D. graduate Xinyuan Cao. "}],"uid":"36532","created_gmt":"2026-05-19 20:41:33","changed_gmt":"2026-05-19 20:45:57","author":"Morgan Usry","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-05-15T00:00:00-04:00","iso_date":"2026-05-15T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680321":{"id":"680321","type":"image","title":"xinyuan_grad-photo.jpeg","body":null,"created":"1779223299","gmt_created":"2026-05-19 20:41:39","changed":"1779223299","gmt_changed":"2026-05-19 20:41:39","alt":"woman standing in front of colorful stairs","file":{"fid":"264568","name":"xinyuan_grad-photo.jpeg","image_path":"\/sites\/default\/files\/2026\/05\/19\/xinyuan_grad-photo.jpeg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/05\/19\/xinyuan_grad-photo.jpeg","mime":"image\/jpeg","size":95258,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/05\/19\/xinyuan_grad-photo.jpeg?itok=5Nfobd0p"}}},"media_ids":["680321"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50875","name":"School of Computer Science"}],"categories":[{"id":"130","name":"Alumni"}],"keywords":[{"id":"195105","name":"2026 Spring Commencement"},{"id":"629","name":"graduation"},{"id":"654","name":"College of Computing"},{"id":"166941","name":"School of Computer Science"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EMorgan Usry, Communications Officer, morgan.usry@cc.gatech.edu\u003C\/p\u003E","format":"limited_html"}],"email":["morgan.usry@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}