add many dois

Author: rafael orozco

docs/paper/paper.bib

@@ -4,6 +4,7 @@ @inproceedings{louboutin2022accelerating
   booktitle={Second International Meeting for Applied Geoscience \& Energy},
   pages={1482--1486},
   year={2022},
+  doi={10.1190/image2022-3750561.1},
   organization={Society of Exploration Geophysicists and American Association of Petroleum~…}
 }
 
@@ -29,6 +30,7 @@ @article{alemohammad2023self
   title={Self-consuming generative models go mad},
   author={Alemohammad, Sina and Casco-Rodriguez, Josue and Luzi, Lorenzo and Humayun, Ahmed Imtiaz and Babaei, Hossein and LeJeune, Daniel and Siahkoohi, Ali and Baraniuk, Richard G},
   journal={arXiv preprint arXiv:2307.01850},
+  doi={10.52591/lxai202312101},
   year={2023}
 }
 
@@ -50,6 +52,7 @@ @article{bezanson2017julia
   number={1},
   pages={65--98},
   year={2017},
+  doi={10.1137/141000671},
   publisher={SIAM},
   url={https://doi.org/10.1137/141000671}
 }
@@ -58,13 +61,15 @@ @article{peters2019symmetric
   title={Symmetric block-low-rank layers for fully reversible multilevel neural networks},
   author={Peters, Bas and Haber, Eldad and Lensink, Keegan},
   journal={arXiv preprint arXiv:1912.12137},
+  doi={10.48550/arXiv.1912.12137},
   year={2019}
 }
 
 @article{orozco2022memory,
   title={Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging},
   author={Orozco, Rafael and Louboutin, Mathias and Herrmann, Felix J},
   journal={arXiv preprint arXiv:2204.11850},
+  doi={10.48550/arXiv.2204.11850},
   year={2022}
 }
 
@@ -84,6 +89,7 @@ @article{innes2019differentiable
   title={A differentiable programming system to bridge machine learning and scientific computing},
   author={Innes, Mike and Edelman, Alan and Fischer, Keno and Rackauckas, Chris and Saba, Elliot and Shah, Viral B and Tebbutt, Will},
   journal={arXiv preprint arXiv:1907.07587},
+  doi={10.48550/arXiv.1907.07587},
   year={2019}
 }
 
@@ -146,10 +152,15 @@ @software{nflows
   url          = {https://doi.org/10.5281/zenodo.4296287}
 }
 
-@article{paszke2017automatic,
-  title={Automatic differentiation in pytorch},
-  author={Paszke, Adam and Gross, Sam and Chintala, Soumith and Chanan, Gregory and Yang, Edward and DeVito, Zachary and Lin, Zeming and Desmaison, Alban and Antiga, Luca and Lerer, Adam},
-  year={2017}
+
+
+@article{paszke2019pytorch,
+  title={Pytorch: An imperative style, high-performance deep learning library},
+  author={Paszke, Adam and Gross, Sam and Massa, Francisco and Lerer, Adam and Bradbury, James and Chanan, Gregory and Killeen, Trevor and Lin, Zeming and Gimelshein, Natalia and Antiga, Luca and others},
+  journal={Advances in neural information processing systems},
+  volume={32},
+  doi={doi.org/10.48550/arXiv.1912.01703},
+  year={2019}
 }
 
 @book{haar1909theorie,
@@ -164,13 +175,15 @@ @article{dinh2014nice
   title={Nice: Non-linear independent components estimation},
   author={Dinh, Laurent and Krueger, David and Bengio, Yoshua},
   journal={arXiv preprint arXiv:1410.8516},
+  doi={10.48550/arXiv.1410.8516},
   year={2014}
 }
 
 @article{dinh2016density,
   title={Density estimation using real nvp},
   author={Dinh, Laurent and Sohl-Dickstein, Jascha and Bengio, Samy},
   journal={arXiv preprint arXiv:1605.08803},
+  doi={10.48550/arXiv.1605.08803},
   year={2016}
 }
 
@@ -181,6 +194,7 @@ @article{lensink2022fully
   volume={9},
   number={4},
   pages={60},
+  doi={10.1007/s40687-022-00343-1},
   year={2022},
   publisher={Springer}
 }
@@ -217,6 +231,7 @@ @inproceedings{kumar2021enabling
   author={Kumar, Rajiv and Kotsi, Maria and Siahkoohi, Ali and Malcolm, Alison},
   booktitle={First International Meeting for Applied Geoscience \& Energy},
   pages={1515--1519},
+  doi={10.1190/segam2021-3583705.1},
   year={2021},
   organization={Society of Exploration Geophysicists}
 }
@@ -235,20 +250,23 @@ @article{siahkoohi2021preconditioned
   title={Preconditioned training of normalizing flows for variational inference in inverse problems},
   author={Siahkoohi, Ali and Rizzuti, Gabrio and Louboutin, Mathias and Witte, Philipp A and Herrmann, Felix J},
   journal={arXiv preprint arXiv:2101.03709},
+  doi={10.48550/arXiv.2101.03709},
   year={2021}
 }
 
 @article{siahkoohi2022wave,
   title={Wave-equation-based inversion with amortized variational Bayesian inference},
   author={Siahkoohi, Ali and Orozco, Rafael and Rizzuti, Gabrio and Herrmann, Felix J},
   journal={arXiv preprint arXiv:2203.15881},
+  doi={10.48550/arXiv.2203.15881},
   year={2022}
 }
 
 @article{orozco2023refining,
   title={Refining Amortized Posterior Approximations using Gradient-Based Summary Statistics},
   author={Orozco, Rafael and Siahkoohi, Ali and Louboutin, Mathias and Herrmann, Felix J},
   journal={arXiv preprint arXiv:2305.08733},
+  doi={10.48550/arXiv.2305.08733},
   year={2023}
 }
 
@@ -299,13 +317,15 @@ @article{gahlot2023inference
   title={Inference of CO2 flow patterns--a feasibility study},
   author={Gahlot, Abhinav Prakash and Erdinc, Huseyin Tuna and Orozco, Rafael and Yin, Ziyi and Herrmann, Felix J},
   journal={arXiv preprint arXiv:2311.00290},
+  doi={10.48550/arXiv.2311.00290},
   year={2023}
 }
 
 @article{orozco2023amortized,
   title={Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantification},
   author={Orozco, Rafael and Louboutin, Mathias and Siahkoohi, Ali and Rizzuti, Gabrio and van Leeuwen, Tristan and Herrmann, Felix},
   journal={arXiv preprint arXiv:2303.03478},
+  doi={10.48550/arXiv.2303.03478},
   year={2023}
 }
 

docs/paper/paper.md

@@ -47,7 +47,7 @@ The package we present, InvertibleNetworks.jl, is a pure Julia [@bezanson2017jul
 # Statement of need
 
 
-This software package focuses on memory efficiency. The promise of neural networks is in learning high-dimensional distributions from examples thus normalizing flow packages should allow easy application to large dimensional inputs such as images or 3D volumes. Interestingly, the invertibility of normalizing flows naturally alleviates memory concerns since intermediate network activations can be recomputed instead of saved in memory, greatly reducing the memory needed during backpropagation. The problem is that directly implementing normalizing flows in automatic differentiation frameworks such as PyTorch [@paszke2017automatic] will not automatically exploit this invertibility. The available packages for normalizing flows such as Bijectors.jl [@fjelde2020bijectors], NormalizingFlows.jl [@NormalizingFlows.jl], nflows [@nflows], normflows [@stimper2023normflows] and FrEIA [@freia] are built depending on automatic differentiation frameworks and thus do not exploit invertibility for memory efficiently. 
+This software package focuses on memory efficiency. The promise of neural networks is in learning high-dimensional distributions from examples thus normalizing flow packages should allow easy application to large dimensional inputs such as images or 3D volumes. Interestingly, the invertibility of normalizing flows naturally alleviates memory concerns since intermediate network activations can be recomputed instead of saved in memory, greatly reducing the memory needed during backpropagation. The problem is that directly implementing normalizing flows in automatic differentiation frameworks such as PyTorch [@paszke2019pytorch] will not automatically exploit this invertibility. The available packages for normalizing flows such as Bijectors.jl [@fjelde2020bijectors], NormalizingFlows.jl [@NormalizingFlows.jl], nflows [@nflows], normflows [@stimper2023normflows] and FrEIA [@freia] are built depending on automatic differentiation frameworks and thus do not exploit invertibility for memory efficiently. 
 
 We chose to write this package in Julia since it was built with a commitment to facilitate interoperability with other packages for workflows in scientific machine learning [@louboutin2022accelerating]. The interoperability was facilitated by the multiple dispatch system of Julia. Our goal is to provide solutions for imaging problems with high degrees of freedom, where computational speed is crucial. We have found that this software significantly benefits from Julia's Just-In-Time compilation technology.