Summer 2022

Deep Learning Theory Workshop and Summer School

Aug 1, 2022 to Aug 5, 2022 

Add to Calendar


Nati Srebro (Toyota Technological Institute at Chicago; chair), Spencer Frei (UC Berkeley), Suriya Gunasekar (Toyota Technological Institute at Chicago), Preetum Nakkiran (UC San Diego), Youngtak Sohn (Massachusetts Institute of Technology), Nati Srebro (Toyota Technological Institute at Chicago)

Much progress has been made over the past several years in understanding computational and statistical issues surrounding deep learning, which lead to changes in the way we think about deep learning, and machine learning theory more broadly.  This includes an emphasis of scale-sensitive complexity control, the power of overparameterization, interpolation learning and the importance of algorithmic regularization and the dynamics of training.  The summer school and workshop will combine tutorials from experts in the field bringing participants up to date on these developments, with workshop talks presenting current and ongoing research.