Foundations of Small DataSpeaker: Professor Pratik Chaudhari, University of PennsylvaniaTime: Thursday, Sept 16, 2021, 10:00AM - 11:00AM, Eastern Time Zoom Link: contact tml.online.seminars@gmail.com Abstract:The relevant limit for machine learning is not N going to infinity but instead N going to 0. The human visual system is proof that it is possible to learn categories with extremely few samples. This talk will discuss steps towards building such systems and it is structured in three parts. The first part will discuss algorithms to adapt representations of deep networks to new categories with few labeled data. The second part will discuss when such adaptation works well and while doing so, it will develop a method to compute the information-theoretically optimal distance between two learning tasks. The third part will discuss tools to learn tasks that are "far away" from each other and will point to new methods for multi-task and continual learning.This talk will discuss results from the following papers. 1. An Information-Geometric Distance on the Space of Tasks. Yansong Gao, Pratik Chaudhari. ICML 2021. paper and code 2. Boosting a Model Zoo for Multi-Task and Continual Learning. Rahul Ramesh, Pratik Chaudhari. paper and code Speaker's BioPratik Chaudhari is an Assistant Professor in Electrical and Systems Engineering and Computer and Information Science at the University of Pennsylvania. He is a member of the GRASP Laboratory. From 2018--19, he was a Senior Applied Scientist at Amazon Web Services and a Postdoctoral Scholar in Computing and Mathematical Sciences at CalTech. Pratik received his PhD (2018) in Computer Science from UCLA, his Master's (2012) and Engineer's (2014) degrees in Aeronautics and Astronautics from MIT and his Bachelor’s degree (2010) from IIT Bombay. He was a part of NuTonomy Inc. (now Aptiv) from 2014--16. |