H.A. Le Thi, V.T. Ho, Online Learning based on Online DCA and Application to Online Classification.

Abstract: We investigate an approach based on DC (difference of convex functions) programming and DCA (dc algorithm) for online learning techniques. The prediction problem of an online learner can be formulated as a DC program for which online DCA is applied. We propose the two so-called complete/approximate versions of online DCA scheme and prove their logarithmic/sublinear regrets. Six online DCA-based algorithms are developed for online binary linear classification. Numerical experiments on a variety of benchmark classification data sets show the efficiency of our proposed algorithms in comparison with the state-of-the-art online classification algorithms.

 

Keywords: Online DC programming, Online DCA, Online learning, Online Classification.

 

Citation: Hoai An Le Thi, Vinh Thanh Ho, Online Learning based on Online DCA and Application to Online Classification. Neural Computation, Volume 32, Issue 4, pp. 759-793, April 2020.

 

Download link