Skip to Main content Skip to Navigation

Advanced machine learning techniques based on DC programming and DCA

Abstract : In this dissertation, we develop some advanced machine learning techniques in the framework of online learning and reinforcement learning (RL). The backbones of our approaches are DC (Difference of Convex functions) programming and DCA (DC Algorithm), and their online version that are best known as powerful nonsmooth, nonconvex optimization tools. This dissertation is composed of two parts: the first part studies some online machine learning techniques and the second part concerns RL in both batch and online modes. The first part includes two chapters corresponding to online classification (Chapter 2) and prediction with expert advice (Chapter 3). These two chapters mention a unified DC approximation approach to different online learning algorithms where the observed objective functions are 0-1 loss functions. We thoroughly study how to develop efficient online DCA algorithms in terms of theoretical and computational aspects. The second part consists of four chapters (Chapters 4, 5, 6, 7). After a brief introduction of RL and its related works in Chapter 4, Chapter 5 aims to provide effective RL techniques in batch mode based on DC programming and DCA. In particular, we first consider four different DC optimization formulations for which corresponding attractive DCA-based algorithms are developed, then carefully address the key issues of DCA, and finally, show the computational efficiency of these algorithms through various experiments. Continuing this study, in Chapter 6 we develop DCA-based RL techniques in online mode and propose their alternating versions. As an application, we tackle the stochastic shortest path (SSP) problem in Chapter 7. Especially, a particular class of SSP problems can be reformulated in two directions as a cardinality minimization formulation and an RL formulation. Firstly, the cardinality formulation involves the zero-norm in objective and the binary variables. We propose a DCA-based algorithm by exploiting a DC approximation approach for the zero-norm and an exact penalty technique for the binary variables. Secondly, we make use of the aforementioned DCA-based batch RL algorithm. All proposed algorithms are tested on some artificial road networks
Complete list of metadatas

Cited literature [131 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Thursday, June 7, 2018 - 4:28:05 PM
Last modification on : Friday, June 8, 2018 - 1:17:14 AM
Long-term archiving on: : Saturday, September 8, 2018 - 2:53:59 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01810274, version 1



Vinh Thanh Ho. Advanced machine learning techniques based on DC programming and DCA. Machine Learning [cs.LG]. Université de Lorraine, 2017. English. ⟨NNT : 2017LORR0289⟩. ⟨tel-01810274⟩



Record views


Files downloads