BEGIN:VCALENDAR METHOD:REQUEST PRODID:Microsoft Exchange Server 2010 VERSION:2.0 BEGIN:VTIMEZONE TZID:Eastern Standard Time BEGIN:STANDARD DTSTART:16010101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11 END:STANDARD BEGIN:DAYLIGHT DTSTART:16010101T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT ORGANIZER;CN="Gupta, Sumeet Kumar":mailto:guptask@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN="Inouye, D avid Iseri":mailto:dinouye@purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=ecefacult y@ecn.purdue.edu:mailto:ecefaculty@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN='ecegrads tudent-list@ecn.purdue.edu':mailto:ecegradstudent-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=ecepostdo cs-list@ecn.purdue.edu:mailto:ecepostdocs-list@ecn.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=BNC-EngSt aff:mailto:BNC-EngStaff@groups.purdue.edu ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=FALSE;CN=Bnc-facul ty-all-list@ecn.purdue.edu:mailto:bnc-faculty-all-list@ecn.purdue.edu ATTACH:CID:5F9700B9923087439760F60F28075D8F@namprd22.prod.outlook.com DESCRIPTION;LANGUAGE=en-US:Unifying and Advancing the Science of Deep Distr ibution Alignment\n\n\n\nProf. David I. Inouye\n\nPurdue University\n\nTue sday\, August 30\, 2022: 4 PM-5 PM\n\nZoom link: https://purdue-edu.zoom.u s/j/3164232249\n\nAbstract\n\nDistribution alignment has the opposite obje ctive of classification. While classification finds a representation that separates two distributions\, alignment finds a representation that brings together two distributions. Alignment has been used in many recent machin e learning applications including domain generalization\, causal discovery \, and fair representation learning. Despite these important applications\ , distribution alignment research lacks a unified and systematic conceptua l framework and has primarily focused on GAN-based adversarial alignment f or images. To address this gap\, I will present a unifying alignment frame work that encompasses alignment concepts\, measures\, algorithms\, and app lications. Specifically\, I will formalize the definition of distribution alignment\, develop novel non-adversarial alignment measures and algorithm s\, and discuss alignment applications in causal discovery and domain gene ralization. Ultimately\, this work aims to advance the science of distribu tion alignment to enable the next generation of contextually aware and rob ust AI systems.\n\n\nBio\n\nProf. David I. Inouye is an assistant professo r in the Elmore Family School of Electrical and Computer Engineering at Pu rdue University. He leads the Probabilistic and Understandable Machine Lea rning Lab\, which focuses on the fundamentals of distribution alignment\, probabilistic models\, and explainable AI. More recently\, he is intereste d in distribution alignment including new alignment algorithms\, measures\ , and applications such as causality and domain generalization. On the exp lainable AI side\, he is interested in distribution shift explanations and tractable uncertainty quantification. Previously\, he was a postdoc at Ca rnegie Mellon University working with Prof. Pradeep Ravikumar. He complete d his Computer Science PhD at The University of Texas at Austin in 2017 ad vised by Prof. Inderjit Dhillon and Prof. Pradeep Ravikumar. He was award ed the NSF Graduate Research Fellowship (NSF GRFP)\n\n\nHost\nSumeet Kumar Gupta\, guptask@purdue.edu\, 765 494 3484\n\n\n UID:040000008200E00074C5B7101A82E008000000001C359E7D99B8D801000000000000000 0100000008680F0D08245C94E8C935DCF52DDB656 SUMMARY;LANGUAGE=en-US:Webinar by Prof. on David I. Inouye "Unifying and Ad vancing the Science of Deep Distribution Alignment" DTSTART;TZID=Eastern Standard Time:20220830T160000 DTEND;TZID=Eastern Standard Time:20220830T170000 CLASS:PUBLIC PRIORITY:5 DTSTAMP:20220825T154844Z TRANSP:OPAQUE STATUS:CONFIRMED SEQUENCE:0 LOCATION;LANGUAGE=en-US:https://purdue-edu.zoom.us/j/3164232249 X-MICROSOFT-CDO-APPT-SEQUENCE:0 X-MICROSOFT-CDO-OWNERAPPTID:2120796700 X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY X-MICROSOFT-CDO-ALLDAYEVENT:FALSE X-MICROSOFT-CDO-IMPORTANCE:1 X-MICROSOFT-CDO-INSTTYPE:0 X-MICROSOFT-DONOTFORWARDMEETING:FALSE X-MICROSOFT-DISALLOW-COUNTER:FALSE X-MICROSOFT-LOCATIONDISPLAYNAME:https://purdue-edu.zoom.us/j/3164232249 X-MICROSOFT-LOCATIONSOURCE:None X-MICROSOFT-LOCATIONS:[{"DisplayName":"https://purdue-edu.zoom.us/j/3164232 249"\,"LocationAnnotation":""\,"LocationUri":""\,"LocationStreet":""\,"Loc ationCity":""\,"LocationState":""\,"LocationCountry":""\,"LocationPostalCo de":""\,"LocationFullAddress":""}] BEGIN:VALARM DESCRIPTION:REMINDER TRIGGER;RELATED=START:-PT15M ACTION:DISPLAY END:VALARM END:VEVENT END:VCALENDAR