The Tea Time Talks 2020: Week Eight

Now that the 2020 Tea Time Talks are on Youtube, you can always have time for tea with Amii and the RLAI Lab! Hosted by Amii’s Chief Scientific Advisory Dr. Richard S. Sutton, these 20-minute talks on technical topics are delivered by students, faculty and guests. The talks are a relaxed and informal way of hearing leaders in AI discuss future lines of research they may explore, with topics ranging from ideas starting to take root to fully-finished projects.

Week eight of the Tea Time Talks features:

Khurram Javed: Learning Causal Models Online

Online learning is an essential property of an intelligent system. Unlike an offline learned system, an online learning system can adapt to changes in the world. Moreover, if the learner has limited capacity, online tracking can achieve better performance even in a stationary world. However, online learning has yet to see the same level of success as batch learning has seen over the past decade -- more specifically, we have not yet seen a scalable online representation learning method.

In this talk, Khurram gives an overview of the online representation learning problem and presents his recent work for discovering causal models online. He also proposes a metric for detecting spurious features online. This metric can be combined with an online representation search algorithm to discover non-spurious features from sensory data. He ends by arguing that by continually removing spurious features online, we can learn models that have strong generalization.

Alan Chan: Problems with Fair ML

In his talk, Alan takes a mostly non-technical dive into the problems of fair ML research today. Beginning with a characterization of fair ML, he then goes through scenarios to tease out problems with this characterization, and concludes with closing questions to improve upon the work being done.

Raksha Kumaraswamy: Stochastic Optimism and Exploration

A predominant theme underlying many methods to promote exploratory behaviour in reinforcement learning is the idea of optimism. In this talk, Raksha takes a closer look at a concrete instantiation of the idea through the lens of Stochastic Optimism. Raksha provides a definition of Stochastic Optimism and describes the framework within which the concept has been proposed (in the literature) to induce effective exploratory behaviour in reinforcement learning.

The Tea Time Talks have now concluded for the year, but stay tuned as we will be uploading the remaining talks in the weeks ahead. In the meantime, you can rewatch or catch up on previous talks on our Youtube playlist.