BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Institut de Science des Données - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Institut de Science des Données
X-ORIGINAL-URL:https://isdm.umontpellier.fr
X-WR-CALDESC:Évènements pour Institut de Science des Données
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20250516T110000
DTEND;TZID=Europe/Paris:20250516T120000
DTSTAMP:20260527T173146
CREATED:20250603T085618Z
LAST-MODIFIED:20250603T085618Z
UID:9926-1747393200-1747396800@isdm.umontpellier.fr
SUMMARY:Unified Breakdown Analysis for Byzantine Robust Gossip
DESCRIPTION:Inria Montpellier\, St-Priest Campus\, Building 5\, Room 02/022\nMachine Learning in Montpellier\, Theory & Practice \nIn decentralized machine learning\, different devices communicate in a peer-to-peer manner to collaboratively learn from each other’s data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG\, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of breakdown point\, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule\, coined CSours\, such that CSours-RG has a near-optimal breakdown. Other choices of aggregation rules lead to existing algorithms such as ClippedGossip or NNA. We give experimental evidence to validate the effectiveness of CSours-RG and highlight the gap with NNA\, in particular against a novel attack tailored to decentralized communications. \n            Visio
URL:https://isdm.umontpellier.fr/event/unified-breakdown-analysis-for-byzantine-robust-gossip-2/
CATEGORIES:Séminaire
ATTACH;FMTTYPE=image/png:https://isdm.umontpellier.fr/wp-content/uploads/2025/06/ml-mpt-ZV3BFD.png
END:VEVENT
END:VCALENDAR