BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Biomedical Mathematics Group
X-ORIGINAL-URL:https://www.ibs.re.kr/bimag
X-WR-CALDESC:Events for Biomedical Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20251229T163000
DTEND;TZID=Asia/Seoul:20251229T183000
DTSTAMP:20260430T184028
CREATED:20251224T001444Z
LAST-MODIFIED:20251224T001528Z
UID:12049-1767025800-1767033000@www.ibs.re.kr
SUMMARY:Distribution shift in machine learning: robustness\, invariance\, and a causal view - Wooseok Ha
DESCRIPTION:Classical machine learning models are typically trained under the assumption that the training (source) and test (target) data are drawn from the same distribution. However\, real-world data are rarely clean or consistent\, and distribution shifts between the source and target domains are ubiquitous. Despite its importance\, addressing distribution shifts is highly difficult. The fundamental challenge is that the problem is mathematically ill-posed: shifts can occur in many different forms\, and no single method can handle all of them. While numerous algorithms have been proposed in recent years to solve distribution shifts\, most are empirical-driven and lack solid foundations. In this talk\, I will provide a broad overview of approaches to address distribution shift based on invariance and distributional robustness\, and explain how these methods are intrinsically connected to a causal perspective. In particular\, I will show why it is crucial to carefully formulate assumptions that relate the source and target domains for reliable generalization\, and how assumptions grounded in the causal system enable the analysis of algorithms under both unsupervised and semi-supervised settings.
URL:https://www.ibs.re.kr/bimag/event/distribution-shift-in-machine-learning-robustness-invariance-and-a-causal-view-wooseok-ha/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Biomedical Mathematics Seminar
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
END:VCALENDAR