Three ways Machine Learning fails and what to do about them

Wednesday, September 23, 2020
11:40 AM - 12:40 PM
Department of Computer Science, 500 W. 120th St., New York, New York 10027
Add to Calendar

Link added to clipboard:

https://events.columbia.edu/cal/event/eventView.do?b=de&calPath=%2Fpublic%2Fcals%2FMainCal&guid=CAL-00bb9e28-746cc741-0174-6e6e661c-00005e15events@columbia.edu&recurrenceId=
CS Distinguished Lecture
Three ways Machine Learning fails and what to do about them
Costis Daskalakis
Online lecture

Hosted by Christos Papadimitriou

Abstract:
A common assumption in machine learning and statistics is the existence of training data comprising independent observations from the entire distribution of relevant data. In practice, data deviates from this assumption in various ways. Data might be biased samples from the distribution of interest, due to systematic selection bias, societal biases, incorrect experimental design, or legal restrictions that might prevent the use of all available data. Moreover, observations might be collected on a social network, a spatial or a temporal domain and may thus not be independent but intricately dependent. Finally, data might be affected by the choices made by other learning agents who are learning and making decisions in the same environment where our data is collected and must be acted upon. In the presence of these deviations from the standard i.i.d. model naively trained models fail. In this talk, we overview recent work with various collaborators suggesting avenues to address the resulting challenges through a combined approach involving tools from truncated statistics, high-dimensional probability, statistical physics, and game theory.

Biography:
Constantinos (aka “Costis”) Daskalakis is a Professor of Electrical Engineering and Computer Science at MIT. He holds a Diploma in Electrical and Computer Engineering from the National Technical University of Athens, and a PhD. in Electrical Engineering and Computer Science from UC Berkeley, advised by Christos Papadimitriou. He works on Computation Theory and its interface with Game Theory, Economics, Probability Theory, Machine Learning and Statistics. He has been honored with the ACM Doctoral Dissertation Award, the Kalai Prize from the Game Theory Society, the Sloan Fellowship in Computer Science, the SIAM Outstanding Paper Prize, the Microsoft Research Faculty Fellowship, the Simons Investigator Award, the Rolf Nevanlinna Prize from the International Mathematical Union, the ACM Grace Murray Hopper Award, and the Bodossaki Foundation Distinguished Young Scientists Award.
Join Zoom Meeting
https://columbiauniversity.zoom.us/j/93027015772?pwd=Mys3MTRQY2lDbkR4dGJaYXEwOU1UUT09
Meeting ID: 930 2701 5772 Passcode: 665132
Event Contact Information:
Daniel Hsu
[email protected]
LOCATION:
  • Online
TYPE:
  • Lecture
CATEGORY:
  • Computer Science
EVENTS OPEN TO:
  • Alumni
  • Faculty
  • Graduate Students
  • Postdocs
  • Public
  • Prospective Students
  • Staff
  • Students
  • Trainees
BACK TO EVENTS

Date Navigation Widget

Filter By

Subscribe Export Options

Getting to Columbia

Other Calendars

Guests With Disabilities