BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.4.0.1//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:369@isdm.umontpellier.fr DTSTART;TZID=Europe/Paris:20240229T140000 DTEND;TZID=Europe/Paris:20240229T140000 DTSTAMP:20260828T111350Z URL:https://isdm.umontpellier.fr/events/differentially-private-coordinate- descent-methods-2/ SUMMARY:Differentially Private Coordinate Descent Methods DESCRIPTION:Room 109\, IMAG\, Triolet campus\n\nMachine Learning in Montpel lier\, Theory &\; Practice\n\nMachine learning'\;s success relies o n the use of datasets that typically hold sensitive information about peop le. To prevent leakage of personal data\, differentially private optimizat ion methods have recently been developed. While these methods offer strong guarantees on data privacy\, they suffer from degraded performance. This incurs a trade-off between data privacy and model utility. In this talk\, I will describe the difficulties faced when training a model with differen tial privacy guarantees\, in particular for high-dimensional models. I wil l then show how coordinate descent methods can exploit structural properti es of the problem to improve the privacy-utility trade-off.\n\nMachine Lea rning in Montpellier\, Theory &\; Practice ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/ 2026/06/ml-mtp-gC78d5.png CATEGORIES:ML MTP LOCATION:Triolet Campus- IMAG - Room 109\, Place Eugène Bataillon\, Montpe llier\, X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Place Eugène Bataillon\, M ontpellier\, ;X-APPLE-RADIUS=100;X-TITLE=Triolet Campus- IMAG - Room 109:g eo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:STANDARD DTSTART:20231029T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD END:VTIMEZONE END:VCALENDAR