To be held online at:
https://videoconf-colibri.zoom.us/j/91599759679No password needed for this session.
Simon Du
28/07/2021, 17:00 — 18:00 Europe/Lisbon — Online
Simon Du, University of Washington
Provable Representation Learning
Representation learning has been widely used in many applications. In this talk, I will present our work, which uncovers when and why representation learning provably improves the sample efficiency, from a statistical learning point of view. I will show
the existence of a good representation among all tasks, and
the diversity of tasks are key conditions that permit improved statistical efficiency via multi-task representation learning.
These conditions provably improve the sample efficiency for functions with certain complexity measures as the representation. If time permits, I will also talk about leveraging the theoretical insights to improve practical performance.
--
FROM 202.121.181.*