BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0.1794427059//EN
X-ORIGINAL-URL:https://www.cmm.uchile.cl/
X-WR-CALNAME:CMM
X-WR-CALDESC:Centro de Modelamiento Matemático
X-WR-TIMEZONE:America/Santiago
BEGIN:VTIMEZONE
TZID:America/Santiago
X-LIC-LOCATION:America/Santiago
BEGIN:STANDARD
TZOFFSETFROM:-0300
TZOFFSETTO:-0300
TZNAME:-03
DTSTART:20261111T165739
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-a0161c65dc9f943adac0381c880e0ad4@cmm.uchile.cl
DTSTART;TZID=America/Santiago:20261111T161500
DTEND;TZID=America/Santiago:20261111T173000
DTSTAMP:20261111T100115Z
CREATED:20261111
LAST-MODIFIED:20261111
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:Chilean Probability Seminar: “A hybrid stochastic Newton algorithm for logistic regression”
DESCRIPTION:Eméric Gbaguidi (University of Bordeaux)\nResumen: We investigate a second-order stochastic algorithm for solving large-scale binary classification problems. We propose to make use of a new hybrid stochastic Newton algorithm that includes two weighted components in the Hessian matrix estimation: the first one coming from the natural Hessian estimate and the second associated with the stochastic gradient information. Our motivation comes from the fact that both parts evaluated at the true parameter of logistic regression, are equal to the Hessian matrix. This new formulation has several advantages and it enables us to prove the almost sure convergence of our stochastic algorithm to the true parameter. Moreover, we significantly improve the almost sure rate of convergence to the Hessian matrix. Furthermore, we establish the central limit theorem for our hybrid stochastic Newton algorithm. Finally, we show a surprising result on the almost sure convergence of the cumulative excess risk.\nEl enlace para conectarse al seminario es:\n\nUnirse a la reunión Zoom\nhttps://reuna.zoom.us/j/84521834914?pwd=OTZ6Y0NWM3pYTGtTbEt3c0luTG96UT09ID de reunión: 845 2183 4914\nCódigo de acceso: 997973\n\n\n
URL:https://www.cmm.uchile.cl/events/chilean-probability-seminar-a-hybrid-stochastic-newton-algorithm-for-logistic-regression/
ORGANIZER;CN=CMM:MAILTO:
CATEGORIES:Seminarios
LOCATION:Sala Maryam Mirzakhani - 6to piso CMM
ATTACH;FMTTYPE=image/jpeg:https://www.cmm.uchile.cl/wp-content/uploads/2026/06/5682-scaled.jpg
END:VEVENT
END:VCALENDAR