Results 131 to 140 of about 884 (184)

On Robustness of the Normalized Subgradient Method with randomly Corrupted Subgradients

, 2020
openaire   +1 more source

A multi-task learning approach combining regression and classification tasks for joint feature selection. [PDF]

Sci Rep
Cao H, Rajan S, Hahn B, Kocak E, Brenner M, Hess F, Schefzik R, Durstewitz D, Koppe G, Schwarz E, Schneider-Lindner V.   +10 more
europepmc   +1 more source

Gradient Descent Provably Escapes Saddle Points in the Training of Shallow ReLU Networks. [PDF]

J Optim Theory Appl
Cheridito P, Jentzen A, Rossmannek F.
europepmc   +1 more source

Distances Between Extension Spaces of Phylogenetic Trees. [PDF]

IEEE Trans Comput Biol Bioinform
Valdez Cabrera MA, Willis AD.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Remarks on subgradients and ?-subgradients

Set-Valued Analysis, 1993
We 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

Incremental Subgradient Methods for Nondifferentiable Optimization [PDF]

SIAM Journal on Optimization, 2001
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Angelia Nedic, Dimitri P Bertsekas
exaly   +2 more sources

Cyclic subgradient projections

Mathematical Programming, 1982
A 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.
Yair Censor, Arnold Lent
openaire   +1 more source

On Convergence Properties of a Subgradient Method

Optimization Methods and Software, 2003
In this article, we consider convergence properties of the normalized subgradient method which employs the stepsize rule based on a priori knowledge of the optimal value of the cost function. We show that the normalized subgradients possess additional information about the problem under consideration, which can be used for improving convergence rates ...
I V Konnov
exaly   +4 more sources

Validation of subgradient optimization

Mathematical Programming, 1974
The "relaxation" procedure introduced by Held and Karp for approximately solving a large linear programming problem related to the traveling-salesman problem is refined and studied experimentally on several classes of specially structured large-scale linear programming problems, and results on the use of the procedure for obtaining exact solutions are ...
Michael Held, Philip Wolfe, Harlan P. Crowder   +2 more
openaire   +1 more source