However, the gradient descent algorithms need to update variables one by one to calculate the loss function with each iteration, which leads to a large amount of computation and a long training time.

Seifu Endris Yimer, Poom Kumam, Parin Chaipunya, Efficient Reduction of Variances in Stochastic Spectral Conjugate Gradient Algorithm, Carpathian Journal of Mathematics, Vol. 41, No. 3 (2025), pp. 849 ...