Generalized conditional gradient: analysis of convergence and applications
arXiv:1510.06567v123 citations
Originality Synthesis-oriented
AI Analysis
This work offers incremental improvements in optimization algorithms for researchers in mathematical optimization.
The paper tackles the analysis of convergence for generalized conditional gradient methods, showing that when the objective function is smooth, the algorithm achieves a linear convergence rate and provides a novel certificate of optimality.
The objectives of this technical report is to provide additional results on the generalized conditional gradient methods introduced by Bredies et al. [BLM05]. Indeed , when the objective function is smooth, we provide a novel certificate of optimality and we show that the algorithm has a linear convergence rate. Applications of this algorithm are also discussed.