Bit-Sized Prophecies
Abstract:
We will dive into the digital crystal ball: Sequential decision-making under uncertainty. This plays a
pivotal role in addressing the dynamic and unpredictable nature of real-world data, and impacts domains
as diverse as weather forecasting and stock market prediction. In this talk we will look at the basic
ingredients of an online learning problem and the challenges it presents. We will also explore some
algorithms that decode the uncertain in 1-Bit prediction problems with expert help.
Speaker Bio
I am a Ph.D. candidate in Computer Science at the Indian Institute of Science (IISc), under Prof. Anand
Louis. Before this, I worked as a Software Developer at Uber. My current research work is broadly on
fairness in algorithms.