Unifying mirror descent and dual averaging
This work addresses optimization challenges for researchers and practitioners in machine learning and related fields, but it appears incremental as it builds on established methods.
The authors tackled the problem of constrained optimization by introducing a new family of first-order algorithms that unifies mirror descent and dual averaging, resulting in new algorithms that significantly outperform existing methods in some situations.
We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations.