SGD with Momentum / Adam Optimizer
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.
Rekod sumber
Petikan disalin secara verbatim daripada rekod sumber kaedah. Tiada pengesahan peringkat tuntutan disimpulkan daripadanya.
- Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR 2015). arXiv:1412.6980. · URL
- Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536. · DOI 10.1038/323533a0
- Polyak, B. T. (1964). Some methods of speeding up the convergence of iteration methods. USSR Computational Mathematics and Mathematical Physics, 4(5), 1–17. · DOI 10.1016/0041-5553(64)90137-5
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 8: Optimization for Training Deep Models). MIT Press. · ISBN 978-0-262-03561-3
Tuntutan yang dikurasi
Tuntutan disimpan dalam lejar bukti, setiap satu dengan penilaiannya sendiri.
Pandangan ini tidak mencipta penilaian tuntutan apabila lejar tiada.
Kaedah berkaitan
Dijana daripada graf kaedah dan ditunjukkan sebagai perhubungan yang dicadangkan mesin — tiada tuntutan bukti disimpulkan.