BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Biomedical Mathematics Group - ECPv6.16.2//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:20250627T140000
DTEND;TZID=Asia/Seoul:20250627T160000
DTSTAMP:20260521T183402
CREATED:20250426T143642Z
LAST-MODIFIED:20250609T001825Z
UID:11067-1751032800-1751040000@www.ibs.re.kr
SUMMARY:Data splitting to avoid information leakage with DataSAIL - Myna Lim
DESCRIPTION:In this talk\, we discuss the paper\, “Data splitting to avoid information leakage with DataSAIL” by Roman Joeres\, et al.\, Nature Communications\, 2025. \nAbstract \nInformation leakage is an increasingly important topic in machine learning research for biomedical applications. When information leakage happens during a model’s training\, it risks memorizing the training data instead of learning generalizable properties. This can lead to inflated performance metrics that do not reflect the actual performance at inference time. We present DataSAIL\, a versatile Python package to facilitate leakage-reduced data splitting to enable realistic evaluation of machine learning models for biological data that are intended to be applied in out-of-distribution scenarios. DataSAIL is based on formulating the problem to find leakage-reduced data splits as a combinatorial optimization problem. We prove that this problem is NP-hard and provide a scalable heuristic based on clustering and integer linear programming. Finally\, we empirically demonstrate DataSAIL’s impact on evaluating biomedical machine learning models.
URL:https://www.ibs.re.kr/bimag/event/data-splitting-to-avoid-information-leakage-with-datasail-myna-lim/
LOCATION:B232 Seminar Room\, IBS\, 55 Expo-ro Yuseong-gu\, Daejeon\, Daejeon\, 34126\, Korea\, Republic of
CATEGORIES:Journal Club
ORGANIZER;CN="Jae Kyoung Kim":MAILTO:jaekkim@kaist.ac.kr
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20250627T160000
DTEND;TZID=Asia/Seoul:20250627T170000
DTSTAMP:20260521T183402
CREATED:20250615T110211Z
LAST-MODIFIED:20250615T110211Z
UID:11180-1751040000-1751043600@www.ibs.re.kr
SUMMARY:U Jin Choi - Simulation-Free Schrodinger Bridges Via Score and Flow Matching (by Tong et al\, AISTATS 2024).
DESCRIPTION:Abstract: 임의로 정한 Initial Distribution Q1 와 Terminal Distribution Q2가 주어 졌을 때 시점과 종점 사이의 contiinious time상에  정의 되는 의미 있는 최적의 Probability Path Measure P 를 찾는 Schrodinger Bridges Problem 은 자연과학\,공학\, 의료 및 생명공학\,경제학 및 금융공학 등의 여러 분야에 나타나는 모델들을 푸는 Unified AI Model 사용 되고 있습니다. Schrodinger Bridges Problem은  유일한 해가 존재 하는 정리는( Follmer\,1988)  증명 되었으므로 데이터를 이용하여  Neural Network Models에 대한 효율적으로 학습방법\,  빠른 알고리즘 연구에 집중 되고 있습니다. Tong et al 연구팀은 2023년 부터 ODE에 기반한 획기적인 생성모델인  Flow Matching for Generative Modeling 기법을  SDE 기반 Diffusion Generative Models에 접목하여 Schrodinger Bridges Problem의 해법을 제시하였습니다.
URL:https://www.ibs.re.kr/bimag/event/u-jin-choi-simulation-free-schrodinger-bridges-via-score-and-flow-matching-by-tong-et-al-aistats-2024/
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