Projected semi-stochastic gradient descent method with mini-batch scheme under weak strong convexity assumption

DOI10.1007/978-3-319-66616-7_7zbMath1383.93096arXiv1612.05356MaRDI QIDQ1695084

Jie Liu, Martin Takáč

Publication date: 6 February 2018

Full work available at URL: https://arxiv.org/abs/1612.05356

zbMATH Keywords

linear convergence; variance reduction; stochastic gradient; support vector machine (SVM); weak strong convexity

Mathematics Subject Classification ID

90C15: Stochastic programming

93E20: Optimal stochastic control

49N15: Duality theory (optimization)

49J55: Existence of optimal solutions to problems involving randomness