Dynamical systems approach to outlier robust deep neural networks for regression for regression based on the
gradient conjugate prior (GCP) updates. We show that contaminating the training data
Gradient methods with regularization for constrained optimization problems and their complexity estimates modifications of conditional
gradient and
gradient projection
methods for smooth convex optimization problems
A method for separation of classes of linear conjugation problems for three-dimensional vector of the homogeneouslinear
conjugation problems for three-dimensional vector, and study their relations with a system of two
Conditional Gradient Method Without Line-Search gradient method, which does not require any line-search procedure. It takes into account the current
Gradient methods with regularization for constrained optimization problems and their complexity estimates modifications of conditional
gradient and
gradient projection
methods for smooth convex optimization problems
Testing the sign-definiteness of forms optimization: the steepest descent
method and the
conjugate gradient method. Theoretical analysis and a