So sánh phương pháp

	SGD với Momentum / Thuật toán tối ưu Adam	Chuẩn hóa theo lô (Batch Normalization)
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2015	2015
Người khởi xướng	Rumelhart, Hinton & Williams (momentum SGD, 1986); Kingma & Ba (Adam, 2015)	Ioffe, S. & Szegedy, C.
Loại	First-order adaptive stochastic optimizer	Normalization technique (applied per mini-batch during training)
Công trình gốc	Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR 2015). arXiv:1412.6980.	Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), PMLR 37, 448–456.
Tên gọi khác	Adam, Adam optimizer, SGD with momentum, momentum SGD	BatchNorm, BN, batch norm, mini-batch normalization
Liên quan	1	1
Tóm tắt	Stochastic Gradient Descent (SGD) with momentum and its adaptive descendant Adam are the foundational parameter-update algorithms used to train virtually every modern deep learning model. Momentum SGD was formalised by Polyak (1964) and brought into neural network training by Rumelhart, Hinton, and Williams (1986). Adam, introduced by Kingma and Ba at ICLR 2015, extended the momentum idea by also maintaining a running average of squared gradients, producing per-parameter adaptive learning rates that make it the default optimizer in contemporary deep learning practice.	Batch Normalization is a training technique introduced by Sergey Ioffe and Christian Szegedy in 2015 that normalizes the pre-activation outputs of each layer using the mean and variance computed over the current mini-batch. By stabilizing the input distribution to each layer throughout training, it substantially reduces internal covariate shift, enabling the use of higher learning rates and making deep networks train faster and more reliably.