Goto

Collaborating Authors

 South America






Learning Augmented Energy Minimization via Speed Scaling

Neural Information Processing Systems

We initiate the study of a variant of the classic online speed scaling problem, in which machine learning predictions about the future can be integrated naturally.






Learning Feature Sparse Principal Subspace

Neural Information Processing Systems

(Algorithm 1). Then, we propose another strategy (Algorithm 2) to solve FSPCA for the general covariance by iteratively building a carefully designed proxy.