BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Rafał Masełek (Jožef Stefan Institute)\, "Machine Learning for 
 BSM Physics searches"
DTSTART:20260304T060000Z
DTEND:20260304T070000Z
DTSTAMP:20260422T175200Z
UID:indico-event-1236@indico.ibs.re.kr
DESCRIPTION:Recent advances in machine learning offer new opportunities to
  enhance searches for Beyond the Standard Model (BSM) physics by enabling 
 more powerful\, flexible\, and computationally efficient data analysis str
 ategies. In this seminar\, I will present recent results from two projects
  focused on the application of neural networks to collider physics. In the
  first part\, I will discuss the development of surrogate likelihood model
 s that accurately approximate full experimental likelihoods\, enabling a s
 ubstantial acceleration of reinterpretation studies and an efficient explo
 ration of high-dimensional BSM parameter spaces\, with direct applications
  to phenomenological analyses. In the second part\, I will introduce a nov
 el anomaly detection framework for data-driven searches for new physics wi
 th minimal theoretical assumptions\, based on unsupervised learning techni
 ques to identify deviations from the Standard Model directly in data\, the
 reby complementing traditional\, signal-driven search strategies and impro
 ving sensitivity to unexpected signatures.\n\nhttps://indico.ibs.re.kr/eve
 nt/1236/
LOCATION:CTPU Seminar room (Theory Bldg\, 4F)
URL:https://indico.ibs.re.kr/event/1236/
END:VEVENT
END:VCALENDAR