Results 141 to 150 of about 22,536 (196)
Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks. [PDF]
J Optim Theory ApplCheridito P, Jentzen A, Rossmannek F.
europepmc +1 more source
Distances Between Extension Spaces of Phylogenetic Trees. [PDF]
IEEE Trans Comput Biol BioinformValdez Cabrera MA, Willis AD.
europepmc +1 more source
Proximal MCMC for Bayesian Inference of Constrained and Regularized Estimation. [PDF]
Am StatZhou X, Heng Q, Chi EC, Zhou H.
europepmc +1 more source
On Robustness of the Normalized Subgradient Method with randomly Corrupted Subgradients
, 2020 openaire +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Conditional subgradient optimization — Theory and applications
European Journal of Operational Research, 1996zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Torbjörn Larsson +2 more
exaly +2 more sources
Remarks on subgradients and ?-subgradients
Set-Valued Analysis, 1993We show that Rockafellar's maximal monotonicity and maximal cyclical monotonicity theorems for subdifferentials can be reformulated and proved for the family of ɛ-subdifferentials of a proper, lower semicontinuous, convex function defined on a normed space. We also show that the subdifferential map of a lower semicontinuous convex function defined on a
Andrei Verona, Maria Elena Verona
openaire +1 more source
Management Science, 1970
There is a dual program linked with every nonlinear program. The dual objective function is called the Lagrangian; it is defined in terms of the original problem. This note presents a characterization of the Lagrangian subgradients under general conditions. The theorem follows from a result of Danskin [1] that can be used (see [2]) to characterize the
openaire +2 more sources
There is a dual program linked with every nonlinear program. The dual objective function is called the Lagrangian; it is defined in terms of the original problem. This note presents a characterization of the Lagrangian subgradients under general conditions. The theorem follows from a result of Danskin [1] that can be used (see [2]) to characterize the
openaire +2 more sources
Cyclic subgradient projections
Mathematical Programming, 1982A cyclically controlled method of subgradient projections (CSP) for the convex feasibility problem of solving convex inequalities is presented. The features of this method make it an efficient tool in handling huge and sparse problems. A particular application to an image reconstruction problem of emission computerized tomography is mentioned.
Censor, Yair, Lent, Arnold
openaire +1 more source