Accelerating adaptive online learning by matrix approximation
International Journal of Data Science and Analytics, pp. 389-400, 2020.
Adaptive subgradient methods are able to leverage the second-order information of functions to improve the regret and have become popular for online learning and optimization. According to the amount of information used, these methods can be divided into diagonal-matrix version (ADA-DIAG) and full-matrix version (ADA-FULL). In practice, A...More
Full Text (Upload PDF)
PPT (Upload PPT)