BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Beyond the Bytes - Ashutosh Trivedi on How do we know an algor
 ithm is treating us fairly?
X-WR-TIMEZONE:Mountain Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20261112T011248Z
UID:tag:localist.com\,2008:EventInstance_53975241896652
DTSTART:20260914T220000Z
DTEND:20260914T225000Z
DESCRIPTION:Please join us for the CS UNDERGRADUATE FACULTY SPEAKER SERIES 
 - “Beyond the Bytes”\n\nAbstract:  Algorithms increasingly influence d
 ecisions about employment\, credit\, healthcare\, taxation\, and access to
  public services. But what does it mean for an algorithm to treat people f
 airly—and how can we verify that it does? Unlike traditional correctness
  requirements\, fairness cannot usually be assessed by examining a single 
 execution. We must compare how the algorithm behaves for different individ
 uals or under different circumstances.\n\nThis talk introduces hyperproper
 ties\, a framework for specifying requirements that relate multiple execut
 ions of a system. Through examples from machine learning\, autonomous syst
 ems\, and tax-preparation software\, we will see how the same perspective 
 can capture fairness\, privacy\, and legal compliance. We will then explor
 e how ideas from logic and formal verification can help determine whether 
 a system satisfies these requirements\, and why doing so is considerably m
 ore challenging than checking conventional safety properties. The talk wil
 l conclude with recent approaches that use mathematical certificates to pr
 ovide guarantees about such relational behavior. No prior background in fo
 rmal methods is required.\n\nBio: Ashutosh Trivedi is an Associate Profess
 or of Computer Science at the University of Colorado Boulder. His research
  lies at the intersection of formal methods\, reinforcement learning\, and
  trustworthy AI\, with an emphasis on providing rigorous guarantees for le
 arning-enabled systems. His current work investigates hyperproperties as a
  framework for reasoning about privacy\, fairness\, and legal compliance\,
  as well as correct-by-construction reinforcement learning for implantable
  medical devices.\n\nTrivedi received the 2022 NSF CAREER Award and a 2024
  Royal Society Wolfson Visiting Fellowship. In 2026\, he received the CEAS
  Outstanding Faculty Research Advisor and Mentor Award. Research from his 
 group has received paper awards at CAV\, HSCC\, and SAS.
LOCATION:ECES 112
SUMMARY:Beyond the Bytes - Ashutosh Trivedi on How do we know an algorithm 
 is treating us fairly?
URL;VALUE=URI:https://calendar.colorado.edu/event/beyond-the-bytes-ashutosh
 -trivedi-on-how-do-we-know-an-algorithm-is-treating-us-fairly
CATEGORIES:Colloquium/Seminar
END:VEVENT
END:VCALENDAR
