Session 2C: Inaugural Lectures by Fellows / Associates
Learning without labels with help from Computational Geometry and Statistical Mechanics
Abstract: Artificial Intelligence (AI) based systems have made rapid progress in the last decade leading to revolutionary changes in several disciplines such as medical imaging, autonomous driving etc. However, most of today's AI systems are largely based on supervised learning wherein the underlying machines are trained by inputs labelled by humans. The ability to learn from the environment without labels, often called unsupervised learning, is now considered as the next big challenge in AI. In this talk, we will focus on the foundations of unsupervised learning where many fundamental challenges remain. Some are statistical in nature, such as Model Complexity and Sample complexity, while some are algorithmic, including the challenge of provably learning the parameters of the model from finite amount of data in polynomial time. I will present several recent results, derived from ideas drawn from the disciplines of Computational Geometry and Statistical Mechanics, which furthers the theory behind several un-supervised learning models.