Loading Events

« All Events

  • This event has passed.

April 17 1:00 pm - 2:15 pm EDT

Title: Robust and Reliable Machine Learning: Progress and Challenges

Speaker: Dimitris Tsipras, Massachusetts Institute of Technology

Date: April 17, 2019

Time: 1:00pm – 2:15pm

Location: Northeastern University, 655 Interdisciplinary Science & Engineering Complex (ISEC), 805 Columbus Ave, Boston MA, 02120

Host: Lydia Zakynthinou, Computer Science Theory at Northeastern

Abstract

Recent progress in machine learning has made the deployment of ML systems in the real world an imminent possibility. But are our current machine learning systems really up to the task?  In this talk, I will discuss the brittleness and vulnerability of the existing ML toolkit. I will then describe a conceptual framework that aims to deliver models that are more reliable, and robust to adversarial manipulation. Finally, I will outline how this framework constitutes a new learning paradigm, how it differs from the classic perspective, and what new challenges it gives rise to.

About the Speaker

Dimitris Tsipras is a PhD student in Computer Science at MIT advised by Aleksander Madry. His work focuses on developing efficient tools for building robust machine learning systems and understanding optimization aspects of deep learning. He has spent time as a research intern at Google Brain and as research assistant in NTUA, Greece.

Details

Date:
April 17
Time:
1:00 pm - 2:15 pm
Event Categories:
, , ,

Venue

ISEC 655
805 Columbus Ave
Boston, MA 02120 United States

Location

Campus
Boston