Colloquium / Seminars
Topic：Towards efficient and rigorous learning with the logarithmic loss
Speaker：Prof. Yen-Huan Li
( Department of Computer Science and Information Engineering, National Taiwan University)
Date time：Nov. 12, 2019 14:00 - 15:00
Tea Party：Nov. 12, 2019 13:30 (SA205)
Minimizing the logarithmic loss is an essential task to many applications, such as positron emission tomography, optimal portfolio selection, and quantum state tomography. The optimization problems are indeed convex. However, the logarithmic loss violates standard smoothness assumptions in optimization literature, so most existing optimization algorithms and/or their convergence guarantees do not directly apply. In this talk, I will introduce some of our recent developments in addressing the logarithmic loss.