BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152639Z
LOCATION:Exhibit Hall
DTSTART;TZID=America/Los_Angeles:20260728T170800
DTEND;TZID=America/Los_Angeles:20260728T170800
UID:dac_DAC 2026_sess306_WIP3263@linklings.com
SUMMARY:Late-Breaking Results: QML for Quantum Sensing under Measurement-I
 nduced Information Loss
DESCRIPTION:Sounak Bhowmik (Southern Methodist University) and Himanshu Th
 apliyal (Southern Methodist University (SMU))\n\nNitrogen-vacancy (NV) cen
 ters in diamond provide a highly sensi-\ntive platform for quantum sensing
 . However, extracting meaningful\ninformation from noisy and lossy measure
 ment data remains a ma-\njor challenge. Quantum machine learning (QML) off
 ers a powerful\nframework for parameter estimation by learning complex rel
 a-\ntionships between quantum sensing data and underlying physical\nsignal
 s. In this work, we demonstrate the role of QML in enhancing\nmagnetic fie
 ld estimation through an NV-center-inspired magne-\ntometry experiment. We
  formulate the sensing task as a regression\nproblem and compare classical
  machine learning models trained\non classical measurement data with quant
 um kernel-based models\ntrained on pre-measurement coherent quantum states
 . Our results\nestablish a theoretical upper bound on sensing performance 
 achiev-\nable when learning from coherent quantum states. These findings\n
 indicate that the effectiveness of QML in quantum sensing critically\ndepe
 nds on access to coherent quantum information. They also\nmotivate future 
 sensing architectures that integrate quantum sen-\nsors with quantum-nativ
 e learning pipelines to unlock improved\nsensing performance\n\nTrack: Stu
 dent\n\n
END:VEVENT
END:VCALENDAR