BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Fairness Constraints on Graphs
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1652880_0
SUMMARY:Fairness Constraints on Graphs
DESCRIPTION:<p>	Speaker: <strong>Rik Sengupta</strong>, UMass Amherst</p><p>	Title: <span><span><span style="color:black">Fairness Constraints on Graphs</span></span></span></p><p>	<span><span><span style="color:black">Abstract: In most of the fair allocation literature about indivisible goods, the fairness constraint under consideration is between *all* pairs of agents. But this is often not representative of the real world, where we only typically care about (and get envious of) the people we actually know. This gives rise to a natural relaxation of many fair allocation problems, where we place agents on the vertices of a graph (representing a system of people knowing some but not all other people), and ask that we only maintain our fairness constraints along the edges of that graph. In this talk, we consider one particular such setting, that of envy-freeness up to any good (EFX). In this setting, we wish to identify graphs G for which, in every instance, an allocation exists that satisfies the EFX constraint along every edge; we call these G-EFX allocations.</span></span></span></p><p>	 </p><p>	As a reminder, we will have talks every Friday, starting sharply at 1:05pm. Most talks this semester (including this week's) are in-person with an option to Zoom in, though a few will be virtual only. The permanent Zoom link for this academic year is below.</p><p>	 </p><p>	The room is on the ground level at the NW corner of the Harvard Science and Engineering Complex, which is open to the public:</p>
LOCATION:SEC 1.413
STATUS:CONFIRMED
DTSTART:20220909T170000Z
DTEND:20220909T183000Z
END:VEVENT
END:VCALENDAR