Search
Search Results
-
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...
-
Fusion Boundary and Gradient Enhancement Network for Camouflage Object Detection
The problems of boundary interruption and missing internal texture feature have not been well solved in the current camouflaged object detection... -
Incremental Natural Gradient Boosting for Probabilistic Regression
The natural gradient boosting method for probabilistic regression... -
Facial depth forgery detection based on image gradient
With the widespread application of deep learning, many artificially generated fake images and videos appear on the Internet. However, it is difficult...
-
RPH-PGD: Randomly Projected Hessian for Perturbed Gradient Descent
The perturbed gradient descent (PGD) method, which adds random noises in the search directions, has been widely used in solving large-scale... -
Mitigating Gradient Inversion Attacks in Federated Learning with Frequency Transformation
Centralised machine learning approaches have raised concerns regarding the privacy of client data. To address this issue, privacy-preserving... -
Multi-index antithetic stochastic gradient algorithm
Stochastic Gradient Algorithms (SGAs) are ubiquitous in computational statistics, machine learning and optimisation. Recent years have brought an...
-
Face super resolution based on attention upsampling and gradient
Face Super-Resolution(SR) is a specific domain SR task, which is to reconstruct low-resolution(LR) face images. Recently, many face super-resolution...
-
Variance Reduction for Deep Q-Learning Using Stochastic Recursive Gradient
Deep Q-learning often suffers from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency.... -
Gradient optimization for object detection in learning with noisy labels
Deep neural networks have made significant progress benefiting large-scale correctly human-labeled datasets. However, large-scale human-labeled...
-
From big data to smart data: a sample gradient descent approach for machine learning
This research paper presents an innovative approach to gradient descent known as ‘‘Sample Gradient Descent’’. This method is a modification of the...
-
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...
-
Model gradient: unified model and policy learning in model-based reinforcement learning
Model-based reinforcement learning is a promising direction to improve the sample efficiency of reinforcement learning with learning a model of the...
-
Complex Gradient Function Based Image Descriptor
Local feature descriptors are widely employed to describe local properties of image patches when constructing a discriminative visual representation...
-
Image dehazing via gradient response and bright region adjustment
The presence of atmospheric haze severely compromises image clarity, contrast, and detail, leading to perceptual confusion for humans and adversely...
-
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...
-
Representing dynamic textures based on polarized gradient features
Efficiently representing dynamic textures (DTs) is one of the significant challenges for video understanding in real implementations of computer...
-
Quantitative Analysis of Gradient Descent Algorithm using scaling methods for improving the prediction process based on Artificial Neural Network
The health development is one of the most important challenges in the world today. All human beings are affected by many diseases due to various...
-
Robust supervised learning with coordinate gradient descent
This paper considers the problem of supervised learning with linear methods when both features and labels can be corrupted, either in the form of...
-
Iterative and mixed-spaces image gradient inversion attack in federated learning
As a distributed learning paradigm, federated learning is supposed to protect data privacy without exchanging users’ local data. Even so, the gradient...