BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Integrating Machine Learning into Algorithm Design
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260817T045409Z
UID:tag:localist.com\,2008:EventInstance_35864878288463
DTSTART:20210304T200000Z
DTEND:20210304T210000Z
DESCRIPTION:Please register here to join us for the CS Colloquium Series 20
 20-21 via Zoom. Once you register\, you will receive a recurring Zoom link
 . You only need to register once to be able to attend any of the seminars.
  \n\n---\n\nAn important property of those algorithms that are typically u
 sed in practice is broad applicability—the ability to solve problems acr
 oss diverse domains. However\, the default\, out-of-the-box performance of
  these algorithms can be unsatisfactory\, with slow runtime\, poor solutio
 n quality\, and even negative long-term social ramifications. In practice\
 , there is often ample data available about the types of problems that an 
 algorithm will be run on\, data that can potentially be harnessed to fine-
 tune the algorithm’s performance. We therefore need principled approache
 s for using this data to obtain strong application-specific performance gu
 arantees.\n\nIn this talk\, I will give an overview of my research that pr
 ovides practical methods built on firm theoretical foundations for incorpo
 rating machine learning and optimization into the process of algorithm des
 ign\, selection\, and configuration. I will describe my contributions acro
 ss several diverse domains\, including integer programming\, clustering\, 
 mechanism design\, and computational biology. As I will demonstrate\, thes
 e seemingly disparate areas are connected by overarching structure which i
 mplies broadly-applicable guarantees.
LOCATION:Zoom
SUMMARY:Integrating Machine Learning into Algorithm Design
URL;VALUE=URI:https://events.seas.harvard.edu/event/guest_speaker_ellen_vit
 ercik_doctoral_research_assistant_carnegie_mellon_university
CATEGORIES:Colloquia / Seminar / Lecture
END:VEVENT
END:VCALENDAR
