SCS Faculty Candidate - Vasilis Kontonis

— 12:00pm

Location:
In Person and Virtual - ET - Gates Hillman 8102 and Zoom

Speaker:
VASILIS KONTONIS , Postdoctoral Research Fellow, Institute for Foundations of Machine Learning, and, Department of Computer Science, University of Texas at Austin
https://vkonton.github.io/

Beyond Worst-Case ML

Worst-case theoretical frameworks provide an overly pessimistic view of what is computationally feasible in machine learning. In this talk, I will present new frameworks and algorithmic results that move beyond worst-case assumptions to enable efficient learning in realistic settings. We will examine why fundamental problems are computationally intractable in the worst case and how to circumvent these barriers.  

I will first discuss robust classification under label noise, introducing efficient algorithms that challenge long-standing impossibility results while improving and generalizing prior algorithmic work. Finally, I will present an application to semi-supervised knowledge distillation, where our principled methods outperform prior works.

 — 

Vasilis Kontonis earned his PhD in Computer Science from the University of Wisconsin-Madison, advised by Professor Christos Tzamos. He is currently a postdoctoral fellow at the Institute for Foundations of Machine Learning (IFML) at the University of Texas at Austin, working with Professor Adam Klivans. His research focuses on designing computationally efficient and provably reliable algorithms in machine learning and statistics. 

He has published in top venues in theoretical computer science and machine learning, including FOCS, STOC, COLT, ICML, and NeurIPS. His work has been recognized with awards, including the Best Paper Award at the Conference on Learning Theory (COLT) 2024. 

In Person and Zoom Participation.  See announcement. 

→ Attendance at this talk is restricted to members of the SCS community and relevant CMU stakeholders.

Add event to Google
Add event to iCal