Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
We present global convergence rates for a line-search method which is based on random first-order models and directions whose quality is ensured only with certain probability. We show that in terms of the order of the accuracy, the evaluation complexity of such a method is the same as its counterpar...
Asıl Yazarlar: | Cartis, C, Scheinberg, K |
---|---|
Materyal Türü: | Journal article |
Baskı/Yayın Bilgisi: |
Springer Berlin Heidelberg
2017
|
Benzer Materyaller
-
Adaptive cubic regularisation methods for unconstrained optimization. Part I: motivation, convergence and numerical results.
Yazar:: Cartis, C, ve diğerleri
Baskı/Yayın Bilgisi: (2011) -
Convergence rate analysis of a stochastic trust-region method via supermartingales
Yazar:: Blanchet, J, ve diğerleri
Baskı/Yayın Bilgisi: (2019) -
Adaptive cubic overestimation methods for unconstrained optimization
Yazar:: Cartis, C, ve diğerleri
Baskı/Yayın Bilgisi: (2007) -
Adaptive cubic overestimation methods for unconstrained optimization
Yazar:: Cartis, C, ve diğerleri
Baskı/Yayın Bilgisi: (2007) -
Global convergence of conjugate gradient method in unconstrained optimization problems
Yazar:: Huda Younus Najm, ve diğerleri
Baskı/Yayın Bilgisi: (2019-10-01)