% Lucid docs — exported BibTeX bibliography.
% Source: data/citations.json
% Entries: 59 canonical + 10 aliases.

@misc{ba_2016,
  title          = {Layer Normalization},
  author         = {Ba},
  year           = {2016},
  eprint         = {1607.06450},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1607.06450}
}

@misc{cooley_1965,
  title          = {An Algorithm for the Machine Calculation of Complex Fourier Series},
  author         = {Cooley},
  year           = {1965},
  doi            = {10.1090/S0025-5718-1965-0178586-1},
  url            = {https://doi.org/10.1090/S0025-5718-1965-0178586-1}
}
%   alias: cooley_tukey_1965

@misc{devlin_2018,
  title          = {BERT: Pre-training of Deep Bidirectional Transformers},
  author         = {Devlin},
  year           = {2018},
  eprint         = {1810.04805},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1810.04805}
}
%   alias: devlin_2019

@misc{dosovitskiy_2020,
  title          = {An Image is Worth 16x16 Words (ViT)},
  author         = {Dosovitskiy},
  year           = {2020},
  eprint         = {2010.11929},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/2010.11929}
}

@misc{dozat_2016,
  title          = {Incorporating Nesterov Momentum into Adam (NAdam)},
  author         = {Dozat},
  year           = {2016},
  url            = {https://openreview.net/forum?id=OM0jvwB8jIp57ZJjtNEZ}
}

@misc{duchi_2011,
  title          = {Adaptive Subgradient Methods (Adagrad)},
  author         = {Duchi},
  year           = {2011},
  url            = {https://jmlr.org/papers/v12/duchi11a.html}
}

@misc{giles_2008,
  title          = {Collected Matrix Derivative Results for Forward and Reverse Mode Algorithmic Differentiation},
  author         = {Giles},
  year           = {2008},
  url            = {https://people.maths.ox.ac.uk/gilesm/files/NA-08-01.pdf}
}

@misc{goodfellow_2014,
  title          = {Generative Adversarial Networks},
  author         = {Goodfellow},
  year           = {2014},
  eprint         = {1406.2661},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1406.2661}
}

@misc{he_2015,
  title          = {Delving Deep into Rectifiers (Kaiming init)},
  author         = {He},
  year           = {2015},
  eprint         = {1502.01852},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1502.01852}
}

@misc{he_2016,
  title          = {Deep Residual Learning (ResNet)},
  author         = {He},
  year           = {2016},
  eprint         = {1512.03385},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1512.03385}
}

@misc{hendrycks_2016,
  title          = {Gaussian Error Linear Units (GELU)},
  author         = {Hendrycks},
  year           = {2016},
  eprint         = {1606.08415},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1606.08415}
}
%   alias: hendrycks_gimpel_2016

@misc{hinton_2012,
  title          = {RMSProp lecture notes},
  author         = {Hinton},
  year           = {2012},
  url            = {https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf}
}

@misc{hirose_2003,
  title          = {Complex-Valued Neural Networks: Theories and Applications},
  author         = {Hirose},
  year           = {2003},
  doi            = {10.1142/5212},
  url            = {https://doi.org/10.1142/5212}
}

@misc{ho_2020,
  title          = {Denoising Diffusion Probabilistic Models},
  author         = {Ho},
  year           = {2020},
  eprint         = {2006.11239},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/2006.11239}
}

@misc{hochreiter_1997,
  title          = {Long Short-Term Memory},
  author         = {Hochreiter},
  year           = {1997},
  doi            = {10.1162/neco.1997.9.8.1735},
  url            = {https://doi.org/10.1162/neco.1997.9.8.1735}
}
%   alias: hochreiter_schmidhuber_1997

@misc{huang_2017,
  title          = {Densely Connected Convolutional Networks (DenseNet)},
  author         = {Huang},
  year           = {2017},
  eprint         = {1608.06993},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1608.06993}
}

@misc{ioffe_2015,
  title          = {Batch Normalization},
  author         = {Ioffe},
  year           = {2015},
  eprint         = {1502.03167},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1502.03167}
}
%   alias: ioffe_szegedy_2015

@misc{kingma_2015,
  title          = {Adam: A Method for Stochastic Optimization},
  author         = {Kingma},
  year           = {2015},
  eprint         = {1412.6980},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1412.6980}
}
%   alias: kingma_ba_2015

@misc{kingma_welling_2014,
  title          = {Auto-Encoding Variational Bayes (VAE)},
  author         = {Kingma and Welling},
  year           = {2014},
  eprint         = {1312.6114},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1312.6114}
}

@misc{klambauer_2017,
  title          = {Self-Normalizing Neural Networks (SELU)},
  author         = {Klambauer},
  year           = {2017},
  eprint         = {1706.02515},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1706.02515}
}

@misc{krizhevsky_2012,
  title          = {ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)},
  author         = {Krizhevsky},
  year           = {2012},
  url            = {https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks}
}

@misc{lecun_1989,
  title          = {Backpropagation Applied to Handwritten Zip Code Recognition},
  author         = {Lecun},
  year           = {1989},
  doi            = {10.1162/neco.1989.1.4.541},
  url            = {https://doi.org/10.1162/neco.1989.1.4.541}
}

@misc{liu_2019,
  title          = {On the Variance of the Adaptive Learning Rate (RAdam)},
  author         = {Liu},
  year           = {2019},
  eprint         = {1908.03265},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1908.03265}
}

@misc{liu_2021,
  title          = {Swin Transformer},
  author         = {Liu},
  year           = {2021},
  eprint         = {2103.14030},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/2103.14030}
}

@misc{liu_2022,
  title          = {A ConvNet for the 2020s (ConvNeXt)},
  author         = {Liu},
  year           = {2022},
  eprint         = {2201.03545},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/2201.03545}
}

@misc{loshchilov_2017,
  title          = {SGDR: Stochastic Gradient Descent with Warm Restarts},
  author         = {Loshchilov},
  year           = {2017},
  eprint         = {1608.03983},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1608.03983}
}
%   alias: loshchilov_hutter_2017

@misc{loshchilov_2019,
  title          = {Decoupled Weight Decay Regularization (AdamW)},
  author         = {Loshchilov},
  year           = {2019},
  eprint         = {1711.05101},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1711.05101}
}
%   alias: loshchilov_hutter_2019

@misc{micikevicius_2018,
  title          = {Mixed Precision Training},
  author         = {Micikevicius},
  year           = {2018},
  eprint         = {1710.03740},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1710.03740}
}

@misc{misra_2019,
  title          = {Mish: A Self Regularized Non-Monotonic Activation Function},
  author         = {Misra},
  year           = {2019},
  eprint         = {1908.08681},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1908.08681}
}

@misc{murray_2016,
  title          = {Differentiation of the Cholesky decomposition},
  author         = {Murray},
  year           = {2016},
  eprint         = {1602.07527},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1602.07527}
}

@misc{oktay_2018,
  title          = {Attention U-Net},
  author         = {Oktay},
  year           = {2018},
  eprint         = {1804.03999},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1804.03999}
}

@misc{polyak_1964,
  title          = {Some methods of speeding up the convergence of iteration methods},
  author         = {Polyak},
  year           = {1964},
  doi            = {10.1016/0041-5553(64)90137-5},
  url            = {https://doi.org/10.1016/0041-5553(64)90137-5}
}

@misc{polyak_ruppert,
  title          = {Acceleration of Stochastic Approximation by Averaging (ASGD)},
  author         = {Polyak and Ruppert},
  doi            = {10.1137/0330046},
  url            = {https://doi.org/10.1137/0330046}
}

@misc{radford_2018,
  title          = {Improving Language Understanding by Generative Pre-Training (GPT)},
  author         = {Radford},
  year           = {2018},
  url            = {https://openai.com/research/language-unsupervised}
}

@misc{radford_2019,
  title          = {Language Models are Unsupervised Multitask Learners (GPT-2)},
  author         = {Radford},
  year           = {2019},
  url            = {https://openai.com/research/better-language-models}
}

@misc{ramachandran_2017,
  title          = {Searching for Activation Functions (Swish)},
  author         = {Ramachandran},
  year           = {2017},
  eprint         = {1710.05941},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1710.05941}
}

@misc{reddi_2018,
  title          = {On the Convergence of Adam and Beyond (AMSGrad)},
  author         = {Reddi},
  year           = {2018},
  eprint         = {1904.09237},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1904.09237}
}

@misc{redmon_2018,
  title          = {YOLOv3},
  author         = {Redmon},
  year           = {2018},
  eprint         = {1804.02767},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1804.02767}
}

@misc{ronneberger_2015,
  title          = {U-Net: Convolutional Networks for Biomedical Image Segmentation},
  author         = {Ronneberger},
  year           = {2015},
  eprint         = {1505.04597},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1505.04597}
}

@misc{simonyan_2014,
  title          = {Very Deep Convolutional Networks (VGG)},
  author         = {Simonyan},
  year           = {2014},
  eprint         = {1409.1556},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1409.1556}
}

@misc{smith_2015,
  title          = {Cyclical Learning Rates for Training Neural Networks},
  author         = {Smith},
  year           = {2015},
  eprint         = {1506.01186},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1506.01186}
}

@misc{smith_2018,
  title          = {Super-Convergence (OneCycleLR)},
  author         = {Smith},
  year           = {2018},
  eprint         = {1803.09820},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1803.09820}
}

@misc{song_2019,
  title          = {Generative Modeling by Estimating Gradients of the Data Distribution},
  author         = {Song},
  year           = {2019},
  eprint         = {1907.05600},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1907.05600}
}

@misc{song_ermon_2019,
  title          = {NCSN: Generative Modeling by Estimating Gradients of the Data Distribution},
  author         = {Song and Ermon},
  year           = {2019},
  eprint         = {1907.05600},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1907.05600}
}

@misc{su_2021,
  title          = {RoFormer: Enhanced Transformer with Rotary Position Embedding},
  author         = {Su},
  year           = {2021},
  eprint         = {2104.09864},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/2104.09864}
}

@misc{sutskever_2013,
  title          = {On the importance of initialization and momentum in deep learning},
  author         = {Sutskever},
  year           = {2013},
  url            = {https://proceedings.mlr.press/v28/sutskever13.html}
}

@misc{szegedy_2014,
  title          = {Going Deeper with Convolutions (GoogLeNet/Inception)},
  author         = {Szegedy},
  year           = {2014},
  eprint         = {1409.4842},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1409.4842}
}

@misc{tan_2019,
  title          = {EfficientNet},
  author         = {Tan},
  year           = {2019},
  eprint         = {1905.11946},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1905.11946}
}

@misc{tieleman_2012,
  title          = {RMSProp (lecture notes, Coursera CSC321)},
  author         = {Tieleman},
  year           = {2012},
  url            = {https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf}
}

@misc{tieleman_hinton_2012,
  title          = {RMSProp (lecture notes)},
  author         = {Tieleman and Hinton},
  year           = {2012},
  url            = {https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf}
}

@misc{townsend_2016,
  title          = {Differentiating the SVD},
  author         = {Townsend},
  year           = {2016},
  url            = {https://j-towns.github.io/papers/svd-derivative.pdf}
}

@misc{vaswani_2017,
  title          = {Attention Is All You Need},
  author         = {Vaswani},
  year           = {2017},
  eprint         = {1706.03762},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1706.03762}
}

@misc{walter_2010,
  title          = {Algorithmic Differentiation in Python with AlgoPy (QR diff)},
  author         = {Walter},
  year           = {2010},
  doi            = {10.1080/10556788.2011.610454},
  url            = {https://doi.org/10.1080/10556788.2011.610454}
}

@misc{walter_lehmann_2010,
  title          = {Algorithmic Differentiation in Python with AlgoPy},
  author         = {Walter and Lehmann},
  year           = {2010},
  doi            = {10.1080/10556788.2011.610454},
  url            = {https://doi.org/10.1080/10556788.2011.610454}
}

@misc{welford_1962,
  title          = {Note on a Method for Calculating Corrected Sums of Squares and Products},
  author         = {Welford},
  year           = {1962},
  doi            = {10.1080/00401706.1962.10490022},
  url            = {https://doi.org/10.1080/00401706.1962.10490022}
}

@misc{wu_2018,
  title          = {Group Normalization},
  author         = {Wu},
  year           = {2018},
  eprint         = {1803.08494},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1803.08494}
}
%   alias: wu_he_2018

@misc{xie_2017,
  title          = {Aggregated Residual Transformations (ResNeXt)},
  author         = {Xie},
  year           = {2017},
  eprint         = {1611.05431},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1611.05431}
}

@misc{zeiler_2012,
  title          = {ADADELTA: An Adaptive Learning Rate Method},
  author         = {Zeiler},
  year           = {2012},
  eprint         = {1212.5701},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1212.5701}
}

@misc{zhang_2019,
  title          = {Root Mean Square Layer Normalization (RMSNorm)},
  author         = {Zhang},
  year           = {2019},
  eprint         = {1910.07467},
  archivePrefix  = {arXiv},
  url            = {https://arxiv.org/abs/1910.07467}
}
%   alias: zhang_sennrich_2019