BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:806@fds.yale.edu
DTSTART;TZID=America/New_York:20241114T160000
DTEND;TZID=America/New_York:20241114T170000
DTSTAMP:20250916T142143Z
URL:https://fds.yale.edu/events/self-proving-models/
SUMMARY:FDS Special Seminar: Orr Paradise (Berkeley)\, "Models that prove t
 heir own correctness"
DESCRIPTION:\nAbstract: This talk introduces Self-Proving models\, a new cl
 ass of models that formally prove the correctness of their outputs via an 
 Interactive Proof system. After reviewing some related literature\, I will
  formally define Self-Proving models and their per-input (worst-case) guar
 antees. I will then present algorithms for learning these models and expla
 in how the complexity of the proof system affects the complexity of the le
 arning algorithms. Finally\, I will show experiments where Self-Proving mo
 dels are trained to compute the Greatest Common Divisor of two integers\, 
 and to prove the correctness of their results to a simple verifier. No pri
 or knowledge of autoregressive models or Interactive Proofs will be assume
 d of the listener. This is a joint work with Noga Amit\, Shafi Goldwasser\
 , and Guy Rothblum.\n\n\n\nSpeaker bio: Orr Paradise is a PhD student in t
 he Theory of Computation group at UC Berkeley\, where he is advised by Sha
 fi Goldwasser and Avishay Tal. Before this\, he completed his MSc at the W
 eizmann Institute of Science under the supervision of Oded Goldreich. His 
 research focuses on theoretical computer science and algorithmic analysis.
  Beyond academia\, Orr works with CETI\, a nonprofit dedicated to decipher
 ing sperm whale communication\, where he contributes theoretical analysis.
  He also serves as Head TA at JamCoders\, a free summer camp that teaches 
 algorithms to high school students in Kingston\, Jamaica.\n\n\n\nWebsite: 
 https://people.eecs.berkeley.edu/~orrp/\n\n\n\nHosted by Ruzica Piskac\n
CATEGORIES:FDS Events,Special Seminar
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th 
 Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
 om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
 E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR