put bib in same dir (easier for me with sublimetext)

mlsys2022style/main.bib

+@INPROCEEDINGS{Vanhaesebrouck2017a,
+  author = {Paul Vanhaesebrouck and Aur\'elien Bellet and Marc Tommasi},
+  title = {{D}ecentralized {C}ollaborative {L}earning of {P}ersonalized {M}odels over {N}etworks},
+  booktitle = {{AISTATS}},
+  year = {2017}
+}
+
+@INPROCEEDINGS{Zantedeschi2020a,
+  author = {Valentina Zantedeschi and Aur\'elien Bellet and Marc Tommasi},
+  title = {{F}ully {D}ecentralized {J}oint {L}earning of {P}ersonalized 
+  {M}odels and {C}ollaboration {G}raphs},
+  booktitle = {{AISTATS}},
+  year = {2020}
+}
+
+
+
+@inproceedings{smith2017federated,
+  title={{Federated Multi-Task Learning}},
+  author={Smith, Virginia and Chiang, Chao-Kai and Sanjabi, Maziar and Talwalkar, Ameet S.},
+  booktitle={NIPS},
+  year={2017}
+}
+
+@inproceedings{perso_fl_mean,
+  title={{Lower Bounds and Optimal Algorithms for Personalized Federated Learning}},
+  author={Filip Hanzely and Slavomír Hanzely and Samuel Horváth and Peter Richtarik},
+  booktitle={NeurIPS},
+  year={2020}
+}
+
+@inproceedings{maml,
+  title={{Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach}},
+  author={Alireza Fallah and Aryan Mokhtari and Asuman Ozdaglar},
+  booktitle={NeurIPS},
+  year={2020}
+}
+
+@inproceedings{moreau,
+  title={{Personalized Federated Learning with Moreau Envelopes}},
+  author={Canh T. Dinh and Nguyen H. Tran and Tuan Dung Nguyen},
+  booktitle={NeurIPS},
+  year={2020}
+}
+
+@techreport{momentum_noniid,
+    title={{Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data}},
+    author={Tao Lin and Sai Praneeth Karimireddy and Sebastian U. Stich and Martin Jaggi},
+    year={2021},
+    institution = {arXiv:2102.04761}
+}
+
+@techreport{tornado,
+    title={TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture},
+    author={Jin-Woo Lee and Jaehoon Oh and Sungsu Lim and Se-Young Yun and Jae-Gil Lee},
+    year={2020},
+    institution = {arXiv:2012.03214}
+}
+
+@techreport{cross_gradient,
+    title={{Cross-Gradient Aggregation for Decentralized Learning from Non-IID data}},
+    author={Yasaman Esfandiari and Sin Yong Tan and Zhanhong Jiang and Aditya Balu and Ethan Herron and Chinmay Hegde and Soumik Sarkar},
+    year={2021},
+    institution = {arXiv:2103.02051}
+}
+
+@techreport{consensus_distance,
+    title={{Consensus Control for Decentralized Deep Learning}},
+    author={Lingjing Kong and Tao Lin and Anastasia Koloskova and Martin Jaggi and Sebastian U. Stich},
+    year={2021},
+    institution = {arXiv:2102.04828}
+}
+
+@INPROCEEDINGS{Colin2016a,
+  author = {Igor Colin and Aur\'elien Bellet and Joseph Salmon and St\'ephan Cl\'emen\c{c}on},
+  title = {{G}ossip {D}ual {A}veraging for {D}ecentralized {O}ptimization of {P}airwise {F}unctions},
+  booktitle = {{ICML}},
+  year = {2016}
+}
+
+@inproceedings{scaffold,
+  title={{SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning}},
+  author={Sai Praneeth Karimireddy and Satyen Kale and Mehryar Mohri and Sashank J. Reddi and Sebastian U. Stich and Ananda Theertha Suresh},
+  booktitle={ICML},
+  year={2020}
+}
+
+@inproceedings{marfoq,
+  title={{Throughput-Optimal Topology Design for Cross-Silo Federated Learning}},
+  author={Othmane Marfoq and Chuan Xu and Giovanni Neglia and Richard Vidal},
+  booktitle={NeurIPS},
+  year={2020}
+}
+
+@inproceedings{Lian2018,
+  Author = {Xiangru Lian and Wei Zhang and Ce Zhang and Ji Liu},
+  Booktitle = {ICML},
+  Title = {{Asynchronous Decentralized Parallel Stochastic Gradient Descent}},
+  Year = {2018}}
+
+@inproceedings{fedprox,
+ author = {Tian Li and Anit Kumar Sahu and Manzil Zaheer and Maziar Sanjabi and Ameet Talwalkar and Virginia Smith},
+ title = {{Federated Optimization in Heterogeneous Networks}},
+ booktitle = {MLSys},
+ year = {2020}
+} 
+
+@inproceedings{quagmire,
+  title={{The Non-IID Data Quagmire of Decentralized Machine Learning}},
+  author={Kevin Hsieh and Amar Phanishayee and Onur Mutlu and Phillip B. Gibbons},
+  booktitle={ICML},
+  year={2020}
+}
+
+@inproceedings{mcmahan2016communication,
+  title={Communication-efficient learning of deep networks from decentralized data},
+  author={McMahan, H. Brendan and Moore, Eider and Ramage, Daniel and Hampson, Seth and Ag\"uera y Arcas, Blaise},
+  booktitle={AISTATS},
+  year={2017}
+}
+
+@inproceedings{neglia2020,
+  title={Decentralized gradient methods: does topology matter?},
+  author={Giovanni Neglia and Chuan Xu and Don Towsley and Gianmarco Calbi},
+  booktitle={AISTATS},
+  year={2020}
+}
+
+@techreport{amp_dec,
+    title={{Privacy Amplification by Decentralization}},
+    author={Edwige Cyffers and Aurélien Bellet},
+    year={2020},
+    institution = {arXiv:2012.05326}
+}
+
+@article{Duchi2012a,
+    Author = {John C. Duchi and Alekh Agarwal and Martin J. Wainwright},
+    Date-Modified = {2014-10-30 15:23:27 +0000},
+    Journal = {{IEEE} {T}ransactions on {A}utomatic {C}ontrol},
+    Keywords = {optimization, distributed},
+    Number = {3},
+    Owner = {aurelien},
+    Pages = {592--606},
+    Timestamp = {2013.09.16},
+    Title = {{D}ual {A}veraging for {D}istributed {O}ptimization: {C}onvergence {A}nalysis and {N}etwork {S}caling},
+    Volume = {57},
+    Year = {2012}}
+
+@article{jelasity,
+    Author = {István Hegedüs and Gábor Danner and Márk Jelasity},
+    Journal = {Journal of Parallel and Distributed Computing},
+    Pages = {109--124},
+    Title = {{Decentralized learning works: An empirical comparison of gossip learning and federated learning}},
+    Volume = {148},
+    Year = {2021}}
+
+@article{Nedic18,
+    Author = {Angelia Nedić and Alex Olshevsky and Michael G. Rabbat},
+    Journal = {Proceedings of the IEEE},
+    Number = {5},
+    Pages = {953--976},
+    Title = {{Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization}},
+    Volume = {106},
+    Year = {2018}}
+
+@techreport{kairouz2019advances,
+    title={{Advances and Open Problems in Federated Learning}},
+    author={Peter Kairouz and others},
+    year={2019},
+    institution = {arXiv:1912.04977}
+}
+
+@article{tibshirani1996regression,
+  title={Regression shrinkage and selection via the lasso},
+  author={Tibshirani, Robert},
+  journal={Journal of the Royal Statistical Society. Series B (Methodological)},
+  pages={267--288},
+  year={1996},
+  publisher={JSTOR}
+}
+@article{candes2009exact,
+  title={Exact matrix completion via convex optimization},
+  author={Cand{\`e}s, Emmanuel J and Recht, Benjamin},
+  journal={Foundations of Computational mathematics},
+  volume={9},
+  number={6},
+  pages={717--772},
+  year={2009},
+  publisher={Springer}
+}
+@article{candes2010power,
+  title={The power of convex relaxation: Near-optimal matrix completion},
+  author={Cand{\`e}s, Emmanuel J and Tao, Terence},
+  journal={IEEE Transactions on Information Theory},
+  volume={56},
+  number={5},
+  pages={2053--2080},
+  year={2010},
+  publisher={IEEE}
+}
+@article{recht2011simpler,
+  title={A simpler approach to matrix completion},
+  author={Recht, Benjamin},
+  journal={Journal of Machine Learning Research},
+  volume={12},
+  number={Dec},
+  pages={3413--3430},
+  year={2011}
+}
+@article{gross2010quantum,
+  title={Quantum state tomography via compressed sensing},
+  author={Gross, David and Liu, Yi-Kai and Flammia, Steven T and Becker, Stephen and Eisert, Jens},
+  journal={Physical review letters},
+  volume={105},
+  number={15},
+  pages={150401},
+  year={2010},
+  publisher={APS}
+}
+@article{gross2011recovering,
+  title={Recovering low-rank matrices from few coefficients in any basis},
+  author={Gross, David},
+  journal={IEEE Transactions on Information Theory},
+  volume={57},
+  number={3},
+  pages={1548--1566},
+  year={2011},
+  publisher={IEEE}
+}
+@article{koltchinskii2011nuclear,
+  title={Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion},
+  author={Koltchinskii, Vladimir and Lounici, Karim and Tsybakov, Alexandre B},
+  journal={The Annals of Statistics},
+  pages={2302--2329},
+  year={2011},
+  publisher={JSTOR}
+}
+@article{bhojanapalli2016global,
+  title={Global Optimality of Local Search for Low Rank Matrix Recovery},
+  author={Bhojanapalli, Srinadh and Neyshabur, Behnam and Srebro, Nathan},
+  journal={arXiv preprint arXiv:1605.07221},
+  year={2016}
+}
+@article{koren2009matrix,
+  title={Matrix factorization techniques for recommender systems},
+  author={Koren, Yehuda and Bell, Robert and Volinsky, Chris and others},
+  journal={Computer},
+  volume={42},
+  number={8},
+  pages={30--37},
+  year={2009},
+  publisher={Institute of Electrical and Electronics Engineers, Inc., 3 Park Avenue, 17 th Fl New York NY 10016-5997 United States}
+}
+@article{candes2015phase,
+  title={Phase retrieval via matrix completion},
+  author={Candes, Emmanuel J and Eldar, Yonina C and Strohmer, Thomas and Voroninski, Vladislav},
+  journal={SIAM review},
+  volume={57},
+  number={2},
+  pages={225--251},
+  year={2015},
+  publisher={SIAM}
+}
+@inproceedings{ji2010robust,
+  title={Robust video denoising using low rank matrix completion.},
+  author={Ji, Hui and Liu, Chaoqiang and Shen, Zuowei and Xu, Yuhong},
+  booktitle={CVPR},
+  pages={1791--1798},
+  year={2010},
+  organization={Citeseer}
+}
+@inproceedings{wu2010robust,
+  title={Robust photometric stereo via low-rank matrix completion and recovery},
+  author={Wu, Lun and Ganesh, Arvind and Shi, Boxin and Matsushita, Yasuyuki and Wang, Yongtian and Ma, Yi},
+  booktitle={Asian Conference on Computer Vision},
+  pages={703--717},
+  year={2010},
+  organization={Springer}
+}
+@inproceedings{goldberg2010transduction,
+  title={Transduction with matrix completion: Three birds with one stone},
+  author={Goldberg, Andrew and Recht, Ben and Xu, Junming and Nowak, Robert and Zhu, Xiaojin},
+  booktitle={Advances in neural information processing systems},
+  pages={757--765},
+  year={2010}
+}
+@inproceedings{xie2014learning,
+  title={Learning from the past: intelligent on-line weather monitoring based on matrix completion},
+  author={Xie, Kun and Wang, Lele and Wang, Xin and Wen, Jigang and Xie, Gaogang},
+  booktitle={Distributed Computing Systems (ICDCS), 2014 IEEE 34th International Conference on},
+  pages={176--185},
+  year={2014},
+  organization={IEEE}
+}
+@inproceedings{cabral2013unifying,
+  title={Unifying nuclear norm and bilinear factorization approaches for low-rank matrix decomposition},
+  author={Cabral, Ricardo and De La Torre, Fernando and Costeira, Jo{\~a}o P and Bernardino, Alexandre},
+  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
+  pages={2488--2495},
+  year={2013}
+}
+@inproceedings{cabral2011matrix,
+  title={Matrix Completion for Multi-label Image Classification.},
+  author={Cabral, Ricardo Silveira and De la Torre, Fernando and Costeira, Jo{\~a}o Paulo and Bernardino, Alexandre},
+  booktitle={NIPS},
+  volume={201},
+  number={1},
+  pages={2},
+  year={2011}
+}
+@inproceedings{zhou2012multi,
+  title={Multi-task learning: Theory, algorithms, and applications},
+  author={Zhou, Jiayu and Chen, Jianhui and Ye, Jieping},
+  booktitle={U RL https://www. siam. org/meetings/sdm12/zhou\_chen\_ye. pdf},
+  year={2012}
+}
+@article{toh1999sdpt3,
+  title={SDPT3—a MATLAB software package for semidefinite programming, version 1.3},
+  author={Toh, Kim-Chuan and Todd, Michael J and T{\"u}t{\"u}nc{\"u}, Reha H},
+  journal={Optimization methods and software},
+  volume={11},
+  number={1-4},
+  pages={545--581},
+  year={1999},
+  publisher={Taylor \& Francis}
+}
+@article{sturm1999using,
+  title={Using SeDuMi 1.02, a MATLAB toolbox for optimization over symmetric cones},
+  author={Sturm, Jos F},
+  journal={Optimization methods and software},
+  volume={11},
+  number={1-4},
+  pages={625--653},
+  year={1999},
+  publisher={Taylor \& Francis}
+}
+@article{cai2010singular,
+  title={A singular value thresholding algorithm for matrix completion},
+  author={Cai, Jian-Feng and Cand{\`e}s, Emmanuel J and Shen, Zuowei},
+  journal={SIAM Journal on Optimization},
+  volume={20},
+  number={4},
+  pages={1956--1982},
+  year={2010},
+  publisher={SIAM}
+}
+@article{ma2011fixed,
+  title={Fixed point and Bregman iterative methods for matrix rank minimization},
+  author={Ma, Shiqian and Goldfarb, Donald and Chen, Lifeng},
+  journal={Mathematical Programming},
+  volume={128},
+  number={1-2},
+  pages={321--353},
+  year={2011},
+  publisher={Springer}
+}
+@inproceedings{hazan2008sparse,
+  title={Sparse approximate solutions to semidefinite programs},
+  author={Hazan, Elad},
+  booktitle={Latin American Symposium on Theoretical Informatics},
+  pages={306--316},
+  year={2008},
+  organization={Springer}
+}
+@inproceedings{jaggi2010simple,
+  title={A simple algorithm for nuclear norm regularized problems},
+  author={Jaggi, Martin and Sulovsk, Marek and others},
+  booktitle={Proceedings of the 27th International Conference on Machine Learning (ICML-10)},
+  pages={471--478},
+  year={2010}
+}
+@article{bellet2014distributed,
+  title={Distributed Frank-Wolfe algorithm: A unified framework for communication-efficient sparse learning},
+  author={Bellet, Aur{\'e}lien and Liang, Yingyu and Garakani, Alireza Bagheri and Balcan, Maria-Florina and Sha, Fei},
+  journal={CoRR, abs/1404.2644},
+  year={2014},
+  publisher={Citeseer}
+}
+@inproceedings{wang2016parallel,
+  title={Parallel and distributed block-coordinate Frank-Wolfe algorithms},
+  author={Wang, Yu-Xiang and Sadhanala, Veeranjaneyulu and Dai, Wei and Neiswanger, Willie and Sra, Suvrit and Xing, Eric},
+  booktitle={International Conference on Machine Learning},
+  pages={1548--1557},
+  year={2016}
+}
+@article{lacoste2012block,
+  title={Block-coordinate Frank-Wolfe optimization for structural SVMs},
+  author={Lacoste-Julien, Simon and Jaggi, Martin and Schmidt, Mark and Pletscher, Patrick},
+  journal={arXiv preprint arXiv:1207.4747},
+  year={2012}
+}
+@article{frank1956algorithm,
+  title={An algorithm for quadratic programming},
+  author={Frank, Marguerite and Wolfe, Philip},
+  journal={Naval research logistics quarterly},
+  volume={3},
+  number={1-2},
+  pages={95--110},
+  year={1956},
+  publisher={Wiley Online Library}
+}
+@article{clarkson2010coresets,
+  title={Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm},
+  author={Clarkson, Kenneth L},
+  journal={ACM Transactions on Algorithms (TALG)},
+  volume={6},
+  number={4},
+  pages={63},
+  year={2010},
+  publisher={ACM}
+}
+@inproceedings{jaggi2013revisiting,
+  title={Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization.},
+  author={Jaggi, Martin},
+  booktitle={ICML (1)},
+  pages={427--435},
+  year={2013}
+}
+@article{pong2010trace,
+  title={Trace norm regularization: Reformulations, algorithms, and multi-task learning},
+  author={Pong, Ting Kei and Tseng, Paul and Ji, Shuiwang and Ye, Jieping},
+  journal={SIAM Journal on Optimization},
+  volume={20},
+  number={6},
+  pages={3465--3489},
+  year={2010},
+  publisher={SIAM}
+}
+@inproceedings{harchaoui2012large,
+  title={Large-scale image classification with trace-norm regularization},
+  author={Harchaoui, Zaid and Douze, Matthijs and Paulin, Mattis and Dudik, Miroslav and Malick, J{\'e}r{\^o}me},
+  booktitle={Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on},
+  pages={3386--3393},
+  year={2012},
+  organization={IEEE}
+}
+@article{ILSVRC15,
+Author = {Olga Russakovsky and Jia Deng and Hao Su and Jonathan Krause and Sanjeev Satheesh and Sean Ma and Zhiheng Huang and Andrej Karpathy and Aditya Khosla and Michael Bernstein and Alexander C. Berg and Li Fei-Fei},
+Title = {{ImageNet Large Scale Visual Recognition Challenge}},
+Year = {2015},
+journal   = {International Journal of Computer Vision (IJCV)},
+doi = {10.1007/s11263-015-0816-y},
+volume={115},
+number={3},
+pages={211-252}
+}
+@inproceedings{he2016deep,
+  title={Deep residual learning for image recognition},
+  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+  pages={770--778},
+  year={2016}
+}
+@misc{chollet2015keras,
+  title={Keras},
+  author={Chollet, Fran\c{c}ois},
+  year={2015},
+  publisher={GitHub},
+  howpublished={\url{https://github.com/fchollet/keras}},
+}
+@article{bach2008consistency,
+  title={Consistency of trace norm minimization},
+  author={Bach, Francis R},
+  journal={Journal of Machine Learning Research},
+  volume={9},
+  number={Jun},
+  pages={1019--1048},
+  year={2008}
+}
+@inproceedings{Zaharia:2010:SCC:1863103.1863113,
+ author = {Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J. and Shenker, Scott and Stoica, Ion},
+ title = {Spark: Cluster Computing with Working Sets},
+ booktitle = {Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing},
+ series = {HotCloud'10},
+ year = {2010},
+ location = {Boston, MA},
+ pages = {10--10},
+ numpages = {1},
+ url = {http://dl.acm.org/citation.cfm?id=1863103.1863113},
+ acmid = {1863113},
+ publisher = {USENIX Association},
+ address = {Berkeley, CA, USA},
+}
+@misc{reduce,
+  publisher={stackoverflow},
+  howpublished={\url{http://stackoverflow.com/questions/37422222/how-to-force-spark-to-perform-reduction-locally}},
+}
+@misc{ht,
+  publisher={hortonworks},
+  howpublished={\url{https://community.hortonworks.com/questions/52561/spark-and-hyper-threading.html}},
+}
+@article{wai2017decentralized,
+  title={Decentralized Frank-Wolfe Algorithm for Convex and Non-convex Problems},
+  author={Wai, Hoi-To and Lafond, Jean and Scaglione, Anna and Moulines, Eric},
+  journal={IEEE Transactions on Automatic Control},
+  year={2017},
+  publisher={IEEE}
+}
+@inproceedings{mcdonald2009efficient,
+  title={Efficient large-scale distributed training of conditional maximum entropy models},
+  author={Mcdonald, Ryan and Mohri, Mehryar and Silberman, Nathan and Walker, Dan and Mann, Gideon S},
+  booktitle={Advances in Neural Information Processing Systems},
+  pages={1231--1239},
+  year={2009}
+}
+@inproceedings{zinkevich2010parallelized,
+  title={Parallelized stochastic gradient descent},
+  author={Zinkevich, Martin and Weimer, Markus and Li, Lihong and Smola, Alex J},
+  booktitle={Advances in neural information processing systems},
+  pages={2595--2603},
+  year={2010}
+}
+@article{dean2008mapreduce,
+  title={MapReduce: simplified data processing on large clusters},
+  author={Dean, Jeffrey and Ghemawat, Sanjay},
+  journal={Communications of the ACM},
+  volume={51},
+  number={1},
+  pages={107--113},
+  year={2008},
+  publisher={ACM}
+}
+@article{kuczynski1992estimating,
+  title={Estimating the largest eigenvalue by the power and Lanczos algorithms with a random start},
+  author={Kuczy{\'n}ski, J and Wo{\'z}niakowski, H},
+  journal={SIAM journal on matrix analysis and applications},
+  volume={13},
+  number={4},
+  pages={1094--1122},
+  year={1992},
+  publisher={SIAM}
+}
+@inproceedings{lacoste2015global,
+  title={On the global linear convergence of Frank-Wolfe optimization variants},
+  author={Lacoste-Julien, Simon and Jaggi, Martin},
+  booktitle={Advances in Neural Information Processing Systems},
+  pages={496--504},
+  year={2015}
+}
+@inproceedings{garber2015faster,
+  title={Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets.},
+  author={Garber, Dan and Hazan, Elad},
+  booktitle={ICML},
+  pages={541--549},
+  year={2015}
+}
+@article{wolfe1970convergence,
+  title={Convergence theory in nonlinear programming},
+  author={Wolfe, Philip},
+  journal={Integer and nonlinear programming},
+  pages={1--36},
+  year={1970},
+  publisher={North-Holland Amsterdam}
+}
+@article{guelat1986some,
+  title={Some comments on Wolfe's ‘away step’},
+  author={Gu{\'e}lat, Jacques and Marcotte, Patrice},
+  journal={Mathematical Programming},
+  volume={35},
+  number={1},
+  pages={110--119},
+  year={1986},
+  publisher={Springer}
+}
+@article{beck2004conditional,
+  title={A conditional gradient method with linear rate of convergence for solving convex linear systems},
+  author={Beck, Amir and Teboulle, Marc},
+  journal={Mathematical Methods of Operations Research},
+  volume={59},
+  number={2},
+  pages={235--247},
+  year={2004},
+  publisher={Springer}
+}
+@article{pena2016neumann,
+  title={On the von Neumann and Frank--Wolfe Algorithms with Away Steps},
+  author={Pena, Javier and Rodr{\'\i}guez, Daniel and Soheili, Negar},
+  journal={SIAM Journal on Optimization},
+  volume={26},
+  number={1},
+  pages={499--512},
+  year={2016},
+  publisher={SIAM}
+}
+@article{damla2008linear,
+  title={Linear convergence of a modified Frank--Wolfe algorithm for computing minimum-volume enclosing ellipsoids},
+  author={Damla Ahipasaoglu, S and Sun, Peng and Todd, Michael J},
+  journal={Optimisation Methods and Software},
+  volume={23},
+  number={1},
+  pages={5--19},
+  year={2008},
+  publisher={Taylor \& Francis}
+}
+@article{nanculef2014novel,
+  title={A novel Frank--Wolfe algorithm. Analysis and applications to large-scale SVM training},
+  author={{\~N}anculef, Ricardo and Frandi, Emanuele and Sartori, Claudio and Allende, H{\'e}ctor},
+  journal={Information Sciences},
+  volume={285},
+  pages={66--99},
+  year={2014},
+  publisher={Elsevier}
+}
+@inproceedings{liu2017approximate,
+  title={Approximate Conditional Gradient Descent on Multi-Class Classification.},
+  author={Liu, Zhuanghua and Tsang, Ivor},
+  booktitle={AAAI},
+  pages={2301--2307},
+  year={2017}
+}
+@article{moharrerdistributing,
+  title={Distributing Frank-Wolfe via Map-Reduce},
+  author={Moharrer, Armin and Ioannidis, Stratis}
+}
+@inproceedings{dudik2012lifted,
+  title={Lifted coordinate descent for learning with trace-norm regularization},
+  author={Dudik, Miroslav and Harchaoui, Zaid and Malick, J{\'e}r{\^o}me},
+  booktitle={Artificial Intelligence and Statistics},
+  pages={327--336},
+  year={2012}
+}
+@article{toh2010accelerated,
+  title={An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems},
+  author={Toh, Kim-Chuan and Yun, Sangwoon},
+  journal={Pacific Journal of Optimization},
+  volume={6},
+  number={615-640},
+  pages={15},
+  year={2010}
+}
+
+@inproceedings{lian2017d-psgd,
+  title = {{Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent}},
+  author = {Lian, Xiangru and Zhang, Ce and Zhang, Huan and Hsieh, Cho-Jui and Zhang, Wei and Liu, Ji},
+  booktitle = {NIPS},
+  year = {2017}
+}
+
+@article{nedic2016sgp, 
+    author={{Nedić}, Angelia and {Olshevsky}, Alex}, 
+    journal={IEEE Transactions on Automatic Control}, 
+    title={Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs}, 
+    year={2016}, 
+    volume={61}, 
+    number={12}, 
+    pages={3936-3947},
+}
+
+@article{assran2019stochastic,
+    title={Stochastic Gradient Push for Distributed Deep Learning},
+    author={Mahmoud Assran and Nicolas Loizou and Nicolas Ballas and Michael Rabbat},
+    year={2019},
+    journal={International Conference on Machine Learning}
+}
+
+@incollection{ketkar2017introduction,
+  title={Introduction to pytorch},
+  author={Ketkar, Nikhil},
+  booktitle={Deep learning with python},
+  pages={195--208},
+  year={2017},
+  publisher={Springer}
+}
+
+@article{boyd2006randomized,
+  title={{Randomized Gossip Algorithms}},
+  author={Boyd, Stephen and Ghosh, Arpita and Prabhakar, Balaji and Shah, Devavrat},
+  journal={IEEE Transactions on Information Theory},
+  volume={52},
+  number={6},
+  pages={2508--2530},
+  year={2006},
+  publisher={IEEE},
+  doi={10.1109/TIT.2006.874516}
+}
+
+@article{kempe2003gossip,
+  title={{Gossip-based Computation of Aggregate Information}},
+  author={Kempe, David and Dobra, Alin and Gehrke, Johannes},
+  journal={Foundations of Computer Science},
+  year={2003},
+  organization={IEEE}
+}
+
+@article{nedic2018network,
+  title={{Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization}},
+  author={Nedi{\'c}, Angelia and Olshevsky, Alex and Rabbat, Michael G},
+  journal={Proceedings of the IEEE},
+  volume={106},
+  number={5},
+  pages={953--976},
+  year={2018},
+  publisher={IEEE}
+}
+
+@inproceedings{tang18a,
+  title = 	 {{$D^2$: Decentralized Training over Decentralized Data}},
+  author = 	 {Tang, Hanlin and Lian, Xiangru and Yan, Ming and Zhang, Ce and Liu, Ji},
+  booktitle = 	 {ICML},
+  year = 	 {2018}
+}
+
+@article{xiao2007distributed,
+  title={{Distributed Average Consensus with Least-Mean-Square Deviation}},
+  author={Xiao, Lin and Boyd, Stephen and Kim, Seung-Jean},
+  journal={Journal of parallel and distributed computing},
+  volume={67},
+  number={1},
+  pages={33--46},
+  year={2007},
+  publisher={Elsevier}
+}
+
+@misc{mnistWebsite,
+  title={{The MNIST database of handwritten digits}},
+  author={LeCun, Yann and Cortes, Corinna and Burges, Christopher J.C.},
+  year={2020},
+  howpublished={\url{http://yann.lecun.com/exdb/mnist/}}
+}
+
+@misc{shallue2018measuring,
+    title={{Measuring the Effects of Data Parallelism on Neural Network Training}},
+    author={Christopher J. Shallue and Jaehoon Lee and Joseph Antognini and Jascha Sohl-Dickstein and Roy Frostig and George E. Dahl},
+    year={2018},
+    eprint={1811.03600},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+
+@article{watts1998collective,
+  title={Collective dynamics of ‘small-world’networks},
+  author={Watts, Duncan J and Strogatz, Steven H},
+  journal={nature},
+  volume={393},
+  number={6684},
+  pages={440--442},
+  year={1998},
+  publisher={Nature Publishing Group}
+}
+
+@book{watts2000small,
+  title={Small worlds: The dynamics of networks between order and randomness},
+  author={Watts, Duncan J},
+  year={2000},
+  publisher={Princeton University Press}
+}
+
+% Random Model Walk !!!
+@article{ormandi2013gossip,
+  title={Gossip learning with linear models on fully distributed data},
+  author={Orm{\'a}ndi, R{\'o}bert and Heged{\H{u}}s, Istv{\'a}n and Jelasity, M{\'a}rk},
+  journal={Concurrency and Computation: Practice and Experience},
+  volume={25},
+  number={4},
+  pages={556--571},
+  year={2013},
+  publisher={Wiley Online Library}
+}
+
+% Random Model Walk application to mobile computing
+@phdthesis{berta2020collaborative,
+  title={Collaborative Mobile Gossip Learning},
+  author={Berta, {\'A}rp{\'a}d},
+  year={2020},
+  school={szte}
+}
+
+% Scalable SGD (fully connected topology but not complete averaging every step and asynchronous local updates)
+@misc{nadiradze2020swarmsgd,
+      title={SwarmSGD: Scalable Decentralized SGD with Local Updates}, 
+      author={Giorgi Nadiradze and Amirmojtaba Sabour and Dan Alistarh and Aditya Sharma and Ilia Markov and Vitaly Aksenov},
+      year={2020},
+      eprint={1910.12308},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+
+% Theoretical analysis of fully decentralized sgd
+% Cite this instead: https://proceedings.icml.cc/paper/2020/file/6c2e49911b68d315555d5b3eb0dd45bf-Paper.pdf
+@article{koloskova2020unified,
+  title={A unified theory of decentralized sgd with changing topology and local updates},
+  author={Koloskova, Anastasia and Loizou, Nicolas and Boreiri, Sadra and Jaggi, Martin and Stich, Sebastian U},
+  journal={arXiv preprint arXiv:2003.10422},
+  year={2020}
+}
+
+@misc{gaur2020training,
+      title={{Training Deep Neural Networks Without Batch Normalization}}, 
+      author={Divya Gaur and Joachim Folz and Andreas Dengel},
+      year={2020},
+      eprint={2008.07970},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+
+@misc{you2017large,
+      title={Large Batch Training of Convolutional Networks}, 
+      author={Yang You and Igor Gitman and Boris Ginsburg},
+      year={2017},
+      eprint={1708.03888},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+
+@misc{wu2018group,
+      title={Group Normalization}, 
+      author={Yuxin Wu and Kaiming He},
+      year={2018},
+      eprint={1803.08494},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+
+@article{krizhevsky2009learning,
+  title={{Learning Multiple Layers of Features from Tiny Images}},
+  author={Krizhevsky, Alex},
+  year={2009},
+  howpublished={\url{https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf}},
+}
+
+@article{xiao2004fast,
+  title={Fast linear iterations for distributed averaging},
+  author={Xiao, Lin and Boyd, Stephen},
+  journal={Systems \& Control Letters},
+  volume={53},
+  number={1},
+  pages={65--78},
+  year={2004},
+  publisher={Elsevier}
+}
+
+@article{jelasity2007gossip,
+  title={Gossip-based peer sampling},
+  author={Jelasity, M{\'a}rk and Voulgaris, Spyros and Guerraoui, Rachid and Kermarrec, Anne-Marie and Van Steen, Maarten},
+  journal={ACM Transactions on Computer Systems (TOCS)},
+  volume={25},
+  number={3},
+  pages={8--es},
+  year={2007},
+  publisher={ACM New York, NY, USA}
+}
+
+@InProceedings{pmlr-v28-sutskever13, 
+    title = {On the importance of initialization and momentum in deep learning}, 
+    author = {Ilya Sutskever and James Martens and George Dahl and Geoffrey Hinton}, 
+    booktitle = {ICML}, 
+    year = {2013}
+}
+
+@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{stoica2003chord,
+  title={Chord: a scalable peer-to-peer lookup protocol for internet applications},
+  author={Stoica, Ion and Morris, Robert and Liben-Nowell, David and Karger, David R and Kaashoek, M Frans and Dabek, Frank and Balakrishnan, Hari},
+  journal={IEEE/ACM Transactions on networking},
+  volume={11},
+  number={1},
+  pages={17--32},
+  year={2003},
+  publisher={IEEE}
+}

mlsys2022style/main.tex

@@ -120,7 +120,7 @@ with further possible gains using a small-world topology across cliques.
 \input{related_work}
 \input{conclu}
 
-\bibliography{../main.bib}
+\bibliography{main.bib}
 \bibliographystyle{mlsys2022}
 
 \input{appendix}