reference.bib

% !Mode:: "TeX:UTF-8"

@article{bottou2018optimization,
	author = {Bottou, L{\'e}on and Curtis, Frank E. and Nocedal, Jorge},
	doi = {10.1137/16M1080173},
	eprint = {https://doi.org/10.1137/16M1080173},
	journal = {SIAM Review},
	keywords = {numerical optimization, machine learning, stochastic gradient methods, algorithm complexity analysis, noise reduction methods, second-order methods},
	number = {2},
	pages = {223-311},
	title = {Optimization Methods for Large-Scale Machine Learning},
	url = {https://doi.org/10.1137/16M1080173},
	volume = {60},
	year = {2018},
	bdsk-url-1 = {https://doi.org/10.1137/16M1080173}}
	
@article{POLYAK19641,
	author = {B.T. Polyak},
	doi = {https://doi.org/10.1016/0041-5553(64)90137-5},
	issn = {0041-5553},
	journal = {USSR Computational Mathematics and Mathematical Physics},
	number = {5},
	pages = {1-17},
	title = {Some methods of speeding up the convergence of iteration methods},
	url = {https://www.sciencedirect.com/science/article/pii/0041555364901375},
	volume = {4},
	year = {1964},
	bdsk-url-1 = {https://doi.org/10.1016/0041-5553(64)90137-5},
	bdsk-url-2 = {https://www.sciencedirect.com/science/article/pii/0041555364901375}}

@inproceedings{nesterov1983method,
	author = {Nesterov, Yurii E},
	booktitle = {Dokl. akad. nauk Sssr},
	date-added = {2021-10-30 10:34:56 +0800},
	date-modified = {2021-11-07 20:31:41 +0800},
	pages = {543--547},
	title = {A method for solving the convex programming problem with convergence rate $\mathcal{O}(1/k^2)$},
	volume = {269},
	year = {1983}}

@book{Goodfellow-et-al-2016,
	author = {Ian Goodfellow and Yoshua Bengio and Aaron Courville},
	date-added = {2021-11-09 17:37:15 +0800},
	date-modified = {2021-11-09 17:37:15 +0800},
	note = {\url{http://www.deeplearningbook.org}},
	publisher = {MIT Press},
	title = {Deep Learning},
	year = {2016}}