On The Convergence of First Order Methods for Quasar-Convex Optimization

Understand

In recent years, the success of deep learning has inspired many researchers to study the optimization of general smooth non-convex functions.

• However, recent works have established pessimistic worst-case complexities for this class functions, which is in stark contrast with their superior performance in real-world applications (e.g.
• training deep neural networks).
• On the other hand, it is found that many popular non-convex optimization problems enjoy certain structured properties which bear some similarities to convexity.