@incollection{macnamara2016operator,
  title={Operator splitting},
  author={MacNamara, Shev and Strang, Gilbert},
  booktitle={Splitting Methods in Communication, Imaging, Science, and Engineering},
  pages={95--114},
  year={2016},
  publisher={Springer}
}

@article{schmidt2017minimizing, 
title={Minimizing finite sums with the stochastic average gradient}, 
author={Schmidt, Mark and Le Roux, Nicolas and Bach, Francis}, 
journal={Mathematical Programming}, 
volume={162}, 
number={1-2}, 
pages={83--112}, 
year={2017}, 
publisher={Springer} 
}

@article{robbins1951stochastic, 
title={A stochastic approximation method}, 
author={Robbins, Herbert and Monro, Sutton}, 
journal={The annals of mathematical statistics}, 
pages={400--407}, 
year={1951}, 
publisher={JSTOR} 
}

@article{cauchy1847methode, 
title={M{'e}thode g{'e}n{'e}rale pour la r{'e}solution des systemes d’{'e}quations simultan{'e}es}, author={Cauchy, Augustin}, 
journal={Comp. Rend. Sci. Paris}, 
volume={25}, 
number={1847}, 
pages={536--538}, 
year={1847} 
}

@article{marchuk1968some,
  title={Some application of splitting-up methods to the solution of mathematical physics problems},
  author={Marchuk, Gurij Ivanovich},
  journal={Aplikace matematiky},
  volume={13},
  number={2},
  pages={103--132},
  year={1968},
  publisher={Institute of Mathematics, Academy of Sciences of the Czech Republic}
}

@article{strang1968construction,
  title={On the construction and comparison of difference schemes},
  author={Strang, Gilbert},
  journal={SIAM Journal on Numerical Analysis},
  volume={5},
  number={3},
  pages={506--517},
  year={1968},
  publisher={SIAM}
}

@article{baker1901further,
  title={Further applications of metrix notation to integration problems},
  author={Baker, Henry Frederick},
  journal={Proceedings of the London Mathematical Society},
  volume={1},
  number={1},
  pages={347--360},
  year={1901},
  publisher={Wiley Online Library}
}

@article{campbell1896law,
  title={On a law of combination of operators bearing on the theory of continuous transformation groups},
  author={Campbell, JE},
  journal={Proceedings of the London Mathematical Society},
  volume={1},
  number={1},
  pages={381--390},
  year={1896},
  publisher={Wiley Online Library}
}

@article{hausdorff1906symbolische,
  title={Die symbolische Exponentialformel in der Gruppentheorie},
  author={Hausdorff, Felix},
  journal={Ber. Verh. Kgl. S{\~A} chs. Ges. Wiss. Leipzig., Math.-phys. Kl.},
  volume={58},
  pages={19--48},
  year={1906}
}

@article{sheng1994global,
  title={Global error estimates for exponential splitting},
  author={Sheng, Qin},
  journal={IMA Journal of Numerical Analysis},
  volume={14},
  number={1},
  pages={27--56},
  year={1994},
  publisher={Oxford University Press}
}

@inproceedings{su2014differential,
  title={A differential equation for modeling Nesterov’s accelerated gradient method: Theory and insights},
  author={Su, Weijie and Boyd, Stephen and Candes, Emmanuel},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2510--2518},
  year={2014}
}

@inproceedings{nesterov1983method,
  title={A method of solving a convex programming problem with convergence rate $O(k^2)$},
  author={Nesterov, Yurii Evgen'evich},
  booktitle={Doklady Akademii Nauk},
  volume={269},
  number={3},
  pages={543--547},
  year={1983},
  organization={Russian Academy of Sciences}
}

@article{osher2016sparse,
  title={Sparse recovery via differential inclusions},
  author={Osher, Stanley and Ruan, Feng and Xiong, Jiechao and Yao, Yuan and Yin, Wotao},
  journal={Applied and Computational Harmonic Analysis},
  volume={41},
  number={2},
  pages={436--469},
  year={2016},
  publisher={Elsevier}
}

@article{wibisono2016variational,
  title={A variational perspective on accelerated methods in optimization},
  author={Wibisono, Andre and Wilson, Ashia C and Jordan, Michael I},
  journal={proceedings of the National Academy of Sciences},
  volume={113},
  number={47},
  pages={E7351--E7358},
  year={2016},
  publisher={National Acad Sciences}
}

@book{helmke2012optimization,
  title={Optimization and dynamical systems},
  author={Helmke, Uwe and Moore, John B},
  year={2012},
  publisher={Springer Science \& Business Media}
}

@article{evtushenko1994stable,
  title={Stable barrier-projection and barrier-Newton methods in linear programming},
  author={Evtushenko, Yuri G and Zhadan, Vitali G},
  journal={Computational Optimization and Applications},
  volume={3},
  number={4},
  pages={289--303},
  year={1994},
  publisher={Springer}
}

@article{kaczmarz1937method,
  author  = {S.~Kaczmarz.},
  title   = {Angenäherte Auflösung von Systemen linearer Gleichungen},
  journal = {Bull. Internat. Acad. Polon.Sci. Lettres A},
  year    = {1937},
  pages   = {335--357}
}

@article{strohmer2009randomized,
  title={A randomized Kaczmarz algorithm with exponential convergence},
  author={Strohmer, Thomas and Vershynin, Roman},
  journal={Journal of Fourier Analysis and Applications},
  volume={15},
  number={2},
  pages={262},
  year={2009},
  publisher={Springer}
}

@article{gower2015randomized,
  title={Randomized iterative methods for linear systems},
  author={Gower, Robert M and Richt{\'a}rik, Peter},
  journal={SIAM Journal on Matrix Analysis and Applications},
  volume={36},
  number={4},
  pages={1660--1690},
  year={2015},
  publisher={SIAM}
}

@inproceedings{needell2014stochastic,
  title={Stochastic gradient descent, weighted sampling, and the randomized kaczmarz algorithm},
  author={Needell, Deanna and Ward, Rachel and Srebro, Nati},
  booktitle={Advances in neural information processing systems},
  pages={1017--1025},
  year={2014}
}

@article{lecun1998gradient,
  title={Gradient-based learning applied to document recognition},
  author={LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
  journal={Proceedings of the IEEE},
  volume={86},
  number={11},
  pages={2278--2324},
  year={1998},
  publisher={Ieee}
}

@article{krizhevsky2009learning,
  title={Learning multiple layers of features from tiny images},
  author={Krizhevsky, Alex and Hinton, Geoffrey and others},
  year={2009},
  publisher={Citeseer}
}

@article{dormand1980family,
  title={A family of embedded Runge-Kutta formulae},
  author={Dormand, John R and Prince, Peter J},
  journal={Journal of computational and applied mathematics},
  volume={6},
  number={1},
  pages={19--26},
  year={1980},
  publisher={Elsevier}
}

@article{shampine1986some,
  title={Some practical runge-kutta formulas},
  author={Shampine, Lawrence F},
  journal={Mathematics of computation},
  volume={46},
  number={173},
  pages={135--150},
  year={1986}
}

@ARTICLE{2020SciPy-NMeth,
       author = {{Virtanen}, Pauli and {Gommers}, Ralf and {Oliphant},
         Travis E. and {Haberland}, Matt and {Reddy}, Tyler and
         {Cournapeau}, David and {Burovski}, Evgeni and {Peterson}, Pearu
         and {Weckesser}, Warren and {Bright}, Jonathan and {van der Walt},
         St{\'e}fan J.  and {Brett}, Matthew and {Wilson}, Joshua and
         {Jarrod Millman}, K.  and {Mayorov}, Nikolay and {Nelson}, Andrew
         R.~J. and {Jones}, Eric and {Kern}, Robert and {Larson}, Eric and
         {Carey}, CJ and {Polat}, {\.I}lhan and {Feng}, Yu and {Moore},
         Eric W. and {Vand erPlas}, Jake and {Laxalde}, Denis and
         {Perktold}, Josef and {Cimrman}, Robert and {Henriksen}, Ian and
         {Quintero}, E.~A. and {Harris}, Charles R and {Archibald}, Anne M.
         and {Ribeiro}, Ant{\^o}nio H. and {Pedregosa}, Fabian and
         {van Mulbregt}, Paul and {Contributors}, SciPy 1. 0},
        title = "{SciPy 1.0: Fundamental Algorithms for Scientific
                  Computing in Python}",
      journal = {Nature Methods},
      year = "2020",
      volume={17},
      pages={261--272},
      adsurl = {https://rdcu.be/b08Wh},
      doi = {https://doi.org/10.1038/s41592-019-0686-2},
}

@article{hansen2018air,
  title={AIR Tools II: algebraic iterative reconstruction methods, improved implementation},
  author={Hansen, Per Christian and J{\o}rgensen, Jakob Sauer},
  journal={Numerical Algorithms},
  volume={79},
  number={1},
  pages={107--137},
  year={2018},
  publisher={Springer}
}

@article{xiao2017fashion,
  title={Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms},
  author={Xiao, Han and Rasul, Kashif and Vollgraf, Roland},
  journal={arXiv preprint arXiv:1708.07747},
  year={2017}
}
@article{beck2009fast,
  title={A fast iterative shrinkage-thresholding algorithm for linear inverse problems},
  author={Beck, Amir and Teboulle, Marc},
  journal={SIAM journal on imaging sciences},
  volume={2},
  number={1},
  pages={183--202},
  year={2009},
  publisher={SIAM}
}

@article{blanes2024splitting,
  title={Splitting and composition methods with embedded error estimators},
  author={Blanes, Sergio and Casas, Fernando and Murua, Ander},
  journal={Acta Numerica},
  volume={33},
  pages={1--161},
  year={2024},
  publisher={Cambridge University Press},
  doi={10.1017/S0962492924000011}
}

@article{huang2022dosnet,
  title={A Deeper Look into Deep Operator Splitting Networks},
  author={Huang, Wanting and Yin, Wotao},
  journal={Journal of Computational Physics},
  volume={498},
  pages={112641},
  year={2024},
  publisher={Elsevier}
}

@article{tibshirani1996lasso,
  title={Regression shrinkage and selection via the lasso},
  author={Tibshirani, Robert},
  journal={Journal of the Royal Statistical Society: Series B (Methodological)},
  volume={58},
  number={1},
  pages={267--288},
  year={1996},
  publisher={Wiley}
}

@article{parikh2014proximal,
  title={Proximal algorithms},
  author={Parikh, Neal and Boyd, Stephen},
  journal={Foundations and Trends in Optimization},
  volume={1},
  number={3},
  pages={127--239},
  year={2014},
  publisher={Now Publishers}
}