Laboratory for Information and Inference Systems – LIONS
We divide our research into two synergistic theory thrusts: information scalable optimization and data acquisition, and learning theory and methods for low-dimensional signal models. These research directions dovetail in order to develop a unified theory and practical toolset for adaptive representations, sampling and computational methods for high-dimensional data that feature structured geometric and combinatorial foundations.
LIONS @ ICML 2020
Six LIONS publications have been accepted to the thirty-seventh International Conference on Machine Learning (ICML). This annual conference will be held this year from Sun July 12th to Sat July 18th, as Virtual Conference Only.
LIONS @ ICLR 2020
A LIONS paper entitled "Lipschitz constant estimation for Neural Networks via sparse polynomial optimization" by Fabian Latorre, Paul Rolland and Volkan Cevher has been accepted to the 8th International Conference on Learning Representations ICLR 2020.