BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:885@fds.yale.edu DTSTART;TZID=America/New_York:20250929T153000 DTEND;TZID=America/New_York:20250929T170000 DTSTAMP:20250929T142345Z URL:https://fds.yale.edu/events/sds-seminar-aaditya-ramdas-cmu/ SUMMARY:S&\;DS Seminar: Aaditya Ramdas (CMU)\, "Bringing closure to FDR control: a general principle for multiple testing" DESCRIPTION:\nAbstract: Since the publication of the seminal Benjamini-Hoch berg paper (the most cited paper in statistics)\, it has been an open prob lem how the “closure principle” applies to controlling the false disco very rate (FDR). As background\, the closure principle\, formulated in a s eminal 1976 paper\, states that every procedure for controlling the famil ywise error rate (FWER) can be recovered or improved via “closed testing ”. \n\n\n\nWe fully settle this open problem by finally developing a cl osure principle not only for FDR\, but every error metric that is an expec tation (including the classical one for FWER as a special case). Also surp risingly\, the new generalized closure principle is formulated using the m odern concept of e-values\, which perhaps explains why it had not been dis covered in the past 30 years despite explicit efforts. \;\n\n\n\nThis theoretical advance has immediate implications for practice: it leads to s urprising improvements to both modern and classical FDR methods (eg: Ben jamini-Yekutieli’s famous 2001 procedure is strictly improved\, as is th e e-BH procedure)\, and it also allows for practitioners to choose the err or metric post-hoc (and sometimes the error level itself).\n\n\n\nhttps:// arxiv.org/abs/2509.02517 is the preprint\, joint work with Ziyu Xu\, Aldo Solari\, Lasse Fischer\, Rianne de Heide\, Jelle Goeman (it is actually a merge of two simultaneous papers).\n\n\n\nSpeaker Bio: Aaditya Ramdas i s a tenured Associate Professor at Carnegie Mellon University in the Depar tments of Statistics and Machine Learning. His work has been recognized by the Presidential Early Career Award (PECASE)\, the highest distinction be stowed by the US government to young scientists\, a Kavli fellowship from the NAS\, a Sloan fellowship in Mathematics\, a CAREER award from the NSF\ , the inaugural COPSS Emerging Leader Award\, the Bernoulli new researcher award and the IMS Peter Hall Early Career Prize\, and faculty research aw ards from Adobe and Google. He was recently elected Fellow of the IMS\, wa s awarded Statistician of the Year by the ASA’s Pittsburgh Chapter\, and is the program chair of AISTATS 2026. \n CATEGORIES:FDS Events,Statistics & Data Science Seminar 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:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR