BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//project/author//NONSGML v1.0//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTEND:20221209T120000Z
UID:385fcd0caa11b728893005ceeefe199b-376
DTSTAMP:19700101T120014Z
DESCRIPTION:Lifelong Learning of Representations with Provable Guarantees
URL;VALUE=URI:https://www.csa.iisc.ac.in/newweb/event/376/lifelong-learning-of-representations-with-provable-guarantees/
SUMMARY:In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample efficiency. We consider the setting where all target tasks can be represented in the span of a small number of unknown linear (or nonlinear) features of the input data and propose a lifelong learning algorithm that maintains and refines the internal feature representation. We prove that for any desired accuracy on all tasks, the dimension of the representation remains close to that of the underlying representation. The resulting algorithm is provably efficient and the sample complexity for input dimension d, m tasks with k total features up to error ϵ is O~((dk^1.5 + km)/ϵ). We also prove a matching lower bound for any lifelong learning algorithm that uses a single task learner as a black box. An empirical study, with a lifelong learning heuristic for deep neural networks, performs favorably on challenging image datasets compared to state-of-the-art continual learning methods.


Speaker Website	https://faculty.cc.gatech.edu/~vempala/


Microsoft teams link:

https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZGE3NDg5NzktMWQ0Zi00MzFmLTg5OTgtMTMyYWM4MWQyYjI2%40thread.v2/0?context=%7b%22Tid%22%3a%226f15cd97-f6a7-41e3-b2c5-ad4193976476%22%2c%22Oid%22%3a%227c84465e-c38b-4d7a-9a9d-ff0dfa3638b3%22%7d


Hosts: Aditya Abhay Lonkar, Rahul Madhavan, Rameesh Paul & Aditya Subramanian
DTSTART:20221209T120000Z
END:VEVENT
END:VCALENDAR