[AIP Seminar]Talk by Prof. Nathan Srebro (Toyota Technological Institute at Chicago)

Thu, 24 Aug 2023 10:30 - 11:30 JST
Online Link visible to participants

Registration is closed

Get invited to future events

Free admission
-Passcode: V86gke7Mvw -Time Zone:JST -The seats are available on a first-come-first-served basis. -When the seats are fully booked, we may stop accepting applications. -Simultaneous interpretation will not be available.


Date and Time:
August 24, 2023: 10:30 am - 11:30 am (JST)
Venue: Online and Open Space at the RIKEN AIP Nihonbashi office*
*The Open Space; AIP researchers are only available.

TITLE: Interpolation Learning and Overfitting with Linear Predictors, Neural Nets and Short Programs

SPEAKER:Prof. Nathan Srebro, Toyota Technological Institute at Chicago

Classical theory, conventional wisdom, and all textbooks, tell us to avoid reaching zero training error and overfitting the noise, and instead balance model fit and complexity. Yet, recent empirical and theoretical results suggest that in many cases overfitting is benign, and even interpolating the training data can lead to good generalization. Can we characterize and understand when overfitting is indeed benign, and when it is catastrophic as classic theory suggests? And can existing theoretical approaches be used to study and explain benign overfitting and the "double descent" curve? I will discuss interpolation learning in linear (and kernel) methods, deep learning, as well as using the universal "minimum description length" or "shortest program" learning rule.

All participants are required to agree with the AIP Seminar Series Code of Conduct.
Please see the URL below.

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.

About this community



Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community