New Directions in Machine Learning Theory (24w5308)

Organizers

Karbasi Amin (Yale University)

Shai Ben-David (University of Waterloo)

(Stanford University)

Description

The Banff International Research Station will host the “New Directions in Machine Learning Theory” workshop in Banff from October 20 - 25, 2024.


Machine learning and artificial intelligence have shown tremendous growth in the last few years. However, much of the success has been driven by empirical research and heuristic methods. In this workshop, we are aiming to bring the theory and practice of ML closer in 3 important directions, all of which center on human-in-the-loop ML. First, it has become clear that the traditional learning theory does not explain the success of the novel training methods, and that interactive learning can accelerate the learning process. Second, ML methods are part of a bigger and interconnected ecosystem and are rarely used in isolation. Third, when ML methods are used in high-stake scenarios, not only their predictions but also how they reached such predictions are important. This workshop aims to make a rigorous step toward a better understanding of the aforementioned limitations and proposing solid solutions.


The Banff International Research Station for Mathematical Innovation and Discovery (BIRS) is a collaborative Canada-US-Mexico venture that provides an environment for creative interaction as well as the exchange of ideas, knowledge, and methods within the Mathematical Sciences, with related disciplines and with industry. The research station is located at The Banff Centre in Alberta and is supported by Canada’s Natural Science and Engineering Research Council (NSERC), the U.S. National Science Foundation (NSF), Alberta’s Advanced Education and Technology, and Mexico’s Consejo Nacional de Ciencia y Tecnología (CONACYT).