BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1681
DTSTAMP:20260204T101430Z
SUMMARY:Fundamental Limits of High-Dimensional Inference under Constrained 
 Observations
DESCRIPTION:Speaker: Neha Sangwan (Halıcıoğlu Data Science Institute\, U
 CSD)\n\nAbstract: \nI will discuss recent work on high-dimensional inferen
 ce from nonlinear and quantized observations\, focusing on generalized lin
 ear measurement models. I will describe information-theoretic limits on re
 covery and simple algorithms that approach these limits under structural a
 ssumptions such as sparsity. I will also discuss extensions to models with
  latent structure\, including mixtures of generalized linear models and qu
 antitative group testing\, highlighting how aggregation and heterogeneity 
 reshape fundamental trade-offs in sample complexity and identifiability.\n
 Short Bio: Neha Sangwan is currently a visiting researcher at the Tata Ins
 titute of Fundamental Research (TIFR) and previously held a postdoctoral p
 osition at the University of California San Diego. She received her PhD fr
 om TIFR\, and her research focuses on information-theoretic foundations of
  high-dimensional inference\, sequential decision-making in quantum system
 s\, and reliable communication under adversarial uncertainty.\n
URL:https://www.tcs.tifr.res.in/web/events/1681
DTSTART;TZID=Asia/Kolkata:20260204T160000
DTEND;TZID=Asia/Kolkata:20260204T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR