Acceleration for proximal stochastic dual coordinate ascent algorithm in solving regularised loss minimisation with ℓ2 norm. Issue 5 (1st March 2018)

• Record Type: Journal Article
• Authors: Tan, Beibei; Liu, Benyong
• Is Part Of: Electronics letters. Volume 54:Issue 5(2018)
• Page Start: 315
• Page End: 317
• Publication Date: 2018-03-01
• Subjects: learning (artificial intelligence) -- support vector machines -- minimisation -- regression analysis; proximal stochastic dual coordinate ascent algorithm -- regularised loss minimisation -- SDCA -- machine learning optimisation problems -- support vector machine -- multiclass SVM -- logistic regression -- ridge regression; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2017.4544
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : An accelerated version of the proximal stochastic dual coordinate ascent (SDCA) algorithm in solving regularised loss minimisation with ℓ 2 norm is presented, wherein a momentum is introduced and the strong theoretical guarantees of SDCA are shared. Moreover, it is also suitable for various key machine learning optimisation problems including support vector machine (SVM), multiclass SVM, logistic regression, and ridge regression. In particular, the Nestrov's estimate sequence technique to adjust the weight coefficient dynamically and conveniently is adopted. It is applied for training linear SVM from the large training dataset. Experimental results show that the proposed method has a competitive classification performance and faster convergence speed than state‐of‐the‐art algorithms.