BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.0.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:969@fds.yale.edu DTSTART;TZID=America/New_York:20260921T160000 DTEND;TZID=America/New_York:20260921T170000 DTSTAMP:20260914T212814Z URL:https://fds.yale.edu/events/sds-seminar-ashwin-pananjady-georgia-tech- computationally-efficient-reductions-between-some-statistical-models/ SUMMARY:S&\;DS Seminar: Ashwin Pananjady (Georgia Tech)\, "Computational ly Efficient Reductions Between Some Statistical Models" DESCRIPTION:\n\n\nAbstract: \;Can a sample from one parametric statisti cal model (the source) be transformed into a sample from a different (targ et) model? Versions of this question were asked as far back as 1950\, and a beautiful asymptotic theory of equivalence between experiments emerged&n bsp\;in the latter half of the 20th century. Motivated by problems spannin g information-computation gaps and differentially private data analysis\, we address the analogous non-asymptotic question in high-dimensional probl ems and with algorithmic considerations. We show how a single observation from some source models can be approximately transformed to a single obser vation from a large class of target models by computationally efficient al gorithms. I will present several such reductions and discuss their applica tions to the aforementioned problems.\n\n\n\nThis is joint work with Mengq i Lou and Guy Bresler.\n CATEGORIES:FDS Events LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th Floor\, Room 1327\, New Haven\, CT\, 06511\, United States X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL E=Yale Institute for Foundations of Data Science:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR