Machine learning has made a tremendous impact on the world through products such as automatic face and object recognition in computer vision, self-driving cars, automatic language translation, and a variety of other products. That said, much of the research on machine learning tends to focus on successful algorithms for specific machine learning tasks. The broader theoretical picture of when and why machine learning algorithms are successful tends to be discussed, instead, in a number of related domains and disciplines spanning applied mathematics, computer science theory, and statistics. This conference will highlight the importance of approximation theory as it is used in mathematics in existing and future machine learning and data science problems.

The conference will begin with two colloquium style talks, one focused on approximation theory and the other focused on machine learning, followed by a variety of related talks.  Further details, including registration and housing information, are at 

http://www.math.purdue.edu/calendar/conferences/machinelearning/

Speakers include 

• Misha Belkin, Ohio State University
• David Bindel, Cornell University
• Paul Constantine, University of Colorado, Boulder
• Sanmi Koyejo, University of Illinois
• Sven Leyffer, Argonne National Labs
• Mauro Maggioni, John Hopkins University
• Yusu Wang, Ohio State University
• Stefan Wild, Argonne National Lab

We are grateful to the Institute for Mathematics and its Applications for providing partial support, which allows us to provide some travel funding, with priority for graduate students.   

There is no registration fee, but please register through the link above for an accurate estimate for food and for funding requests.  Please forward to others who may be interested.  We're looking forward to a great conference!  
 
Greg Buzzard, David Gleich, and Guang Lin
Conference Organizers