no code implementations • ICLR 2019 • Mohammadreza Soltani, Swayambhoo Jain, Abhinav V. Sambasivan
Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions.
no code implementations • 2 Oct 2015 • Abhinav V. Sambasivan, Jarvis D. Haupt
This paper examines fundamental error characteristics for a general class of matrix completion problems, where the matrix of interest is a product of two a priori unknown matrices, one of which is sparse, and the observations are noisy.