Login
Talks & Seminars
Title: Some Recent Advances in Learning from User Behavior
Dr. Adith Swaminathan, Microsoft Research
Date & Time: November 22, 2019 17:00
Venue: Department of Computer Science and Engineering, Room No. 109, 01st Floor, New CSE/CC Building
Abstract:
Many of the most impactful applications of machine learning are not just about prediction, but are about putting user-interactive systems in control of selecting the right action at the right time. These systems are both producers and users of data -- the logs of the selected actions and their outcomes can provide valuable training data for improving the system, giving rise to some of the biggest datasets we have collected. Machine learning in these settings is challenging since the system in operation biases the log data through the actions it selects and outcomes remain unknown for the actions not taken. Learning methods must, hence, reason about how changes to the system will affect future outcomes. We will summarize recent advances in these counterfactual learning techniques, and sketch some open problems in the area.
Speaker Profile:
Adith Swaminathan is a senior researcher in the Reinforcement Learning group at Microsoft Research AI. He studies machine learning and counterfactual reasoning techniques to improve user-interactive systems. His research on off-policy learning and understanding user-interaction biases has been applied in several large-scale applications like search engines, recommender systems, ad serving platforms, and interactive games. He completed his PhD at Cornell University (2017) and received a BTech from IIT Bombay (2010).
List of Talks

Webmail

Username:
Password:
Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback