HIGHLIGHTS
- who: Weijia Shao from the Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin, Ernst‑Reuter‑Platz, Berlin, Germany have published the research work: Optimistic optimisation of composite objective with exponentiated update, in the Journal: (JOURNAL)
- what: The authors propose a sorting based procedure projecting the solution to the decision set for the 𝓁1 or nuclear ball constrained problems. The authors show that the converted algorithms guarantee an optimal accelerated convergence rate for smooth objective functions. Following the idea of HU, the authors propose more practical algorithms interpolating EG and the p-norm . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.