• CG_DESCENT

  • Referenced in 122 articles [sw04813]
  • Algorithm 851: CG_DESCENT. A conjugate gradient method with guaranteed descent Recently, a new nonlinear ... conjugate gradient scheme was developed which satisfies the descent condition gTkdk ... extensive numerical tests and comparisons with other methods for large-scale unconstrained optimization are given...
  • Pegasos

  • Referenced in 98 articles [sw08752]
  • contrast, previous analyses of stochastic gradient descent methods for SVMs require Ω(1/ϵ2) iterations...
  • SNLSDP

  • Referenced in 38 articles [sw05127]
  • starting point for a gradient descent method with backtracking line search to solve the smooth...
  • TIGRA

  • Referenced in 40 articles [sw02333]
  • presented. The TIGRA (Tikhonov-gradient method) algorithm proposed uses steepest descent iterations in an inner...
  • Wirtinger Flow

  • Referenced in 83 articles [sw34175]
  • initialization obtained by means of a spectral method, and then refines this initial estimate ... computational complexity, much like in a gradient descent scheme. The main contribution is that this ... patterns. We illustrate the effectiveness of our methods with various experiments on image data. Underlying...
  • LASSO

  • Referenced in 32 articles [sw02850]
  • gradient descent algorithm for LASSO LASSO is a useful method to achieve the shrinkage...
  • BADMM

  • Referenced in 26 articles [sw20288]
  • Alternating Direction Method of Multipliers. The mirror descent algorithm (MDA) generalizes gradient descent by using ... paper, we similarly generalize the alternating direction method of multipliers (ADMM) to Bregman ADMM (BADMM...
  • topopt_multi

  • Referenced in 17 articles [sw25723]
  • Cahn system and regularized projected steepest descent method. A new computational algorithm is introduced ... gradient flow of the objective functional by a fractional step projected steepest descent method...
  • hgm

  • Referenced in 2 articles [sw25628]
  • package hgm: Holonomic Gradient Method and Gradient Descent. The holonomic gradient method (HGM, hgm) gives ... difference equations. The holonomic gradient descent (HGD, hgd) gives a method to find maximal likelihood...
  • SEISCOPE

  • Referenced in 4 articles [sw19396]
  • which implement first-order methods (steepest-descent and nonlinear conjugate gradient) and second-order methods...
  • ADMM-Softmax

  • Referenced in 1 article [sw32744]
  • solving multinomial logistic regression (MLR) problems. Our method is geared toward supervised classification tasks with ... quasi Newton, and a stochastic gradient descent method...
  • GPFEM

  • Referenced in 3 articles [sw22222]
  • Pitaevskii energy: a steepest descent method based on Sobolev gradients and a minimization algorithm based...
  • DNSPLIN1

  • Referenced in 2 articles [sw01235]
  • strain energy by a descent method with a Sobolev gradient in place of the standard...
  • etas_solve

  • Referenced in 2 articles [sw26918]
  • based on the steepest descent method and calculates exact gradient and Hessian using the automatic...
  • LSGA

  • Referenced in 1 article [sw02836]
  • segmentation. Level-set-based segmentation methods typically perform gradient descent minimization on an energy function ... features: the Gabor wavelet based textural segmentation method [1, 9], and the level-set based...
  • DARTS

  • Referenced in 7 articles [sw36213]
  • discrete and non-differentiable search space, our method is based on the continuous relaxation ... efficient search of the architecture using gradient descent. Extensive experiments on CIFAR-10, ImageNet, Penn...
  • NESVM

  • Referenced in 6 articles [sw08753]
  • primal SVM. Then the optimal gradient method without any line search is adopted to solve ... current gradient and historical gradients are combined to determine the descent direction, while the Lipschitz ... smooth parameter and using the continuation method. Our experiments on census income categorization, indoor/outdoor scene...
  • Oger

  • Referenced in 2 articles [sw09696]
  • sets, gradient descent training, several cross-validation schemes and parallel parameter optimization methods. Additionally, several...
  • deepNN

  • Referenced in 1 article [sw38663]
  • Learning methods. Includes multilayer perceptron, different activation functions, regularisation strategies, stochastic gradient descent and dropout...
  • ACDS

  • Referenced in 3 articles [sw31742]
  • Yu.E. Nesterov proposed accelerated gradient-free methods for solving such problems. Since only unconditional optimization ... this statement. We propose an accelerated descent method along a random direction with ... extend this approach to an accelerated gradient-free method). We obtain estimates of the rate...