Stochastic Gradient Descent (SGD) 随机梯度下降
Introducing SGD
AI:
Stochastic Gradient Descent (SGD) is a popular optimization algorithm used in machine learning for finding the minimum of a cost function. It is a variant of the gradient descent algorithm that iteratively updates the parameters of a model by computing the gradient of the cost function with respect to the parameters using a small subset of the training data at each iteration.
In other words, instead of computing the gradient of the cost function for the entire dataset, SGD randomly selects a small batch of training data at each iteration and computes the gradient of the cost function only on that batch. This results in faster convergence and reduced computation time since the algorithm doesn’t need to process the entire dataset in each iteration.
SGD can be used for a w