Search
Search Results
-
Conjugate Gradient Method for finding Optimal Parameters in Linear Regression
Linear regression is one of the most celebrated approaches for modeling the relationship between independent and dependent variables in a prediction...
-
Gradient Method for Solving Singular Optimal Control Problems
Solving an optimal control problem consists in finding a control structure and corresponding switching times. Unlike in a bang-bang case, switching...
-
Stochastic three-term conjugate gradient method with variance technique for non-convex learning
In the training process of machine learning, the minimization of the empirical risk loss function is often used to measure the difference between the...
-
Learning with noisy labels via logit adjustment based on gradient prior method
Robust loss functions are crucial for training models with strong generalization capacity in the presence of noisy labels. The commonly used Cross...
-
Two novel numerical methods for gradient flows: generalizations of the Invariant Energy Quadratization method
In this paper, we conduct an in-depth investigation of the structural intricacies inherent to the Invariant Energy Quadratization (IEQ) method as...
-
TRBoost: a generic gradient boosting machine based on trust-region method
Gradient Boosting Machines (GBMs) have achieved remarkable success in effectively solving a wide range of problems by leveraging Taylor expansions in...
-
Boundedness and Convergence of Mini-batch Gradient Method with Cyclic Dropconnect and Penalty
Dropout is perhaps the most popular regularization method for deep learning. Due to the stochastic nature of the Dropout mechanism, the convergence...
-
A new structured spectral conjugate gradient method for nonlinear least squares problems
Least squares models appear frequently in many fields, such as data fitting, signal processing, machine learning, and especially artificial...
-
A regularized limited memory subspace minimization conjugate gradient method for unconstrained optimization
In this paper, based on the limited memory techniques and subspace minimization conjugate gradient (SMCG) methods, a regularized limited memory...
-
An improved Riemannian conjugate gradient method and its application to robust matrix completion
This paper presents a new conjugate gradient method on Riemannian manifolds and establishes its global convergence under the standard Wolfe line...
-
Preconditioned Gradient Method for Data Approximation with Shallow Neural Networks
A preconditioned gradient scheme for the regularized minimization problem arising from the approximation of given data by a shallow neural network is...
-
Trans-IFFT-FGSM: a novel fast gradient sign method for adversarial attacks
Deep neural networks (DNNs) are popular in image processing but are vulnerable to adversarial attacks, which makes their deployment in...
-
WSAGrad: a novel adaptive gradient based method
The vanishing gradient problem under nonconvexity is an important issue when training a deep neural network. The problem becomes prominent in the...
-
Differential Privacy in Federated Dynamic Gradient Clip** Based on Gradient Norm
Federal learning achieves privacy preservation by adding noise to gradient. The noise needs to be clipped to prevent excessive noise from...
-
An inertial spectral conjugate gradient projection method for constrained nonlinear pseudo-monotone equations
Consider the nonlinear pseudo-monotone equations over a nonempty closed convex set. A spectral conjugate gradient projection method with the inertial...
-
A gradient fusion-based image data augmentation method for reflective workpieces detection under small size datasets
Various of Convolutional Neural Network-based object detection models have been widely used in the industrial field. However, the high accuracy of...
-
A modified conjugate gradient method for general convex functions
The aim of this paper is to introduce a new non-smooth conjugate gradient method for solving unconstrained minimization problems. The proposed method...
-
Adversarial Attacks on Visual Objects Using the Fast Gradient Sign Method
Adversarial attacks exploit vulnerabilities or weaknesses in the model’s decision-making process to generate inputs that appear benign to humans but...
-
A cell-based smoothed finite-element method for gradient elasticity
In this paper, the cell-based smoothed finite-element method (CS-FEM) is proposed for solving boundary value problems of gradient elasticity in two...
-
FCGSM: Fast Conjugate Gradient Sign Method for Adversarial Attack on Image Classification
Deep neural network is sensitive to adversarial samples that crafted by adding imperceptible perturbations to original images, and many methods of...