BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Learning With and From People
DTSTART:20170323T101500
DTEND:20170323T113000
DTSTAMP:20260408T105356Z
UID:b13ba0e03f3bbaaf9eac69564560d175276ce4ad475a70c37da46e43
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Adish Singla - ETH Zurich\nIC Faculty candidate\n\nAbstra
 ct :\nPeople are becoming an integral part of computational systems\, fuel
 ed primarily by recent technological advancements as well as deep-seated e
 conomic and societal changes. Consequently\, there is a pressing need to d
 esign new data science and machine learning frameworks that can tackle cha
 llenges arising from human participation (e.g. questions about incentives 
 and users’ privacy) and can leverage people’s capabilities (e.g. abili
 ty to learn).\n \nIn this talk\, I will share my research efforts at the 
 confluence of people and computing to address real-world problems. Specifi
 cally\, I will focus on collaborative consumption systems (e.g. shared mob
 ility systems and sharing economy marketplaces like Airbnb) and showcase t
 he need to actively engage users for shaping the demand who would otherwis
 e act primarily in their own interest. The main idea of engaging users is 
 to incentivize them to switch to alternate choices that would improve the 
 system’s effectiveness. To offer optimized incentives\, I will present n
 ovel multi-armed bandit algorithms and online learning methods in structur
 ed spaces for learning users’ costs for switching between different pair
 s of available choices. Furthermore\, to tackle the challenges of data spa
 rsity and to speed up learning\, I will introduce hemimetrics as a structu
 ral constraint over users’ preferences. I will show experimental results
  of applying the proposed algorithms on two real-world applications: incen
 tivizing users to explore unreviewed hosts on services like Airbnb and tac
 kling the imbalance problem in bike sharing systems. In collaboration with
  an ETH Zurich spinoff and a public transport operator in the city of Main
 z\, Germany\, we deployed these algorithms via a smartphone app among user
 s of a bike sharing system. I will share the findings from this deployment
 .\n\nBio :\nAdish Singla is a PhD student in the Learning and Adaptive Sys
 tems Group at ETH Zurich. His research focuses on designing new machine le
 arning frameworks and developing algorithmic techniques\, particularly for
  situations where people are an integral part of computational systems. Be
 fore starting his PhD\, he worked as a Senior Development Lead in Bing Sea
 rch for over three years. He is a recipient of the Facebook Fellowship in 
 the area of Machine Learning\, Microsoft Research Tech Transfer Award\, an
 d Microsoft Gold Star Award.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR