{"type":"ScholarlyArticle","title":"Communication-Efficient Stochastic Gradient Descent Ascent with Momentum Algorithms","authors":[{"name":"Yihan Zhang","slug":"yihan-zhang","given":"Yihan","family":"Zhang","affiliation":"Temple University , Philadelphia , PA , USA"},{"name":"Meikang Qiu","slug":"meikang-qiu","given":"Meikang","family":"Qiu","affiliation":"Dakota State University , Madison , SD , USA"},{"name":"Hongchang Gao","slug":"hongchang-gao","given":"Hongchang","family":"Gao","affiliation":"Temple University , Philadelphia , PA , USA"}],"abstract":"Numerous machine learning models can be formulated as a stochastic minimax optimization problem, such as imbalanced data classification with AUC maximization. \r\nDeveloping efficient algorithms to optimize such kinds of problems is of importance and necessity. However, most existing algorithms restrict their focus on the single-machine setting so that they are incapable of dealing with the large communication overhead in a distributed training system. Moreover, most existing communication-efficient optimization algorithms only focus on the traditional minimization problem, failing to handle the minimax optimization problem. To address these challenging issues, in this paper, we develop two novel communication-efficient stochastic gradient descent ascent with momentum algorithms for the distributed minimax optimization problem, which can significantly reduce the communication cost via the two-way compression scheme. However, the compressed momentum makes it considerably challenging to investigate the convergence rate of our algorithms, especially in the presence of the interaction between the minimization and maximization subproblems. In this paper, we successfully addressed these challenges and established the convergence rate of our algorithms for nonconvex-strongly-concave problems. To the best of our knowledge, our algorithms are the first communication-efficient algorithm with theoretical guarantees for the minimax optimization problem. Finally, we apply our algorithm to the distributed AUC maximization problem for the imbalanced data classification task. Extensive experimental results confirm the efficacy of our algorithm in saving communication costs.","doi":"10.24963/ijcai.2023/512","url":"https://ijcai.org/proceedings/2023/512","pdf":"https://ijcai.org/proceedings/2023/0512.pdf","markdown":"https://ijcai.org/proceedings/2023/512.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/512","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":512,"pages":{"first":4602,"last":4610},"keywords":["Machine Learning: ML: Optimization","Data Mining: DM: Parallel, distributed and cloud-based high performance mining","Machine Learning: ML: Federated learning"],"videos":[],"references":[{"position":1,"raw":"[Alistarh et al., 2017] Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. Qsgd: Communication-efficient sgd via gradient quantization and encoding. Advances in Neural Information Process- ing Systems, 30, 2017.","title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","authors":"Alistarh","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Alistarh et al., 2018] Dan Alistarh, Torsten Hoefler, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, and Cédric Renggli. The convergence of sparsified gradient methods. Advances in Neural Information Processing Systems, 31, 2018.","title":"The convergence of sparsified gradient methods","authors":"Dan Alistarh, Torsten Hoefler, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Cédric Renggli","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bernstein et al., 2018] Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, and Animashree Anandkumar. signsgd: Compressed optimisation for non-convex prob- lems. In International Conference on Machine Learning, pages 560-569. PMLR, 2018.","title":"signsgd: Compressed optimisation for non-convex problems","authors":"Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Animashree Anandkumar","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2021] Tianyi Chen, Yuejiao Sun, and Wotao Yin. Closing the gap: Tighter analysis of alternating stochastic gradient methods for bilevel problems. Ad- vances in Neural Information Processing Systems, 34, 2021.","title":"Closing the gap: Tighter analysis of alternating stochastic gradient methods for bilevel problems","authors":"Chen","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Coates et al., 2011] Adam Coates, Andrew Ng, and Honglak Lee. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelli- gence and statistics, pages 215-223. JMLR Workshop and Conference Proceedings, 2011.","title":"An analysis of single-layer networks in unsupervised feature learning","authors":"Adam Coates, Andrew Ng, Honglak Lee","year":"2011","venue":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cutkosky and Orabona, 2019] Ashok Cutkosky and Francesco Orabona. Momentum-based variance reduction in non-convex sgd. Advances in neural information processing systems, 32, 2019.","title":"Momentum-based variance reduction in non-convex sgd","authors":"Ashok Cutkosky, Francesco Orabona","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deng and Mahdavi, 2021] Yuyang Deng and Mehrdad Mahdavi. Local stochastic gradient descent ascent: Convergence analysis and communication efficiency. In International Conference on Artificial Intelligence and Statistics, pages 1387-1395. PMLR, 2021.","title":"Local stochastic gradient descent ascent: Convergence analysis and communication efficiency","authors":"Mahdavi Deng, Yuyang Deng, Mehrdad Mahdavi","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fang et al., 2018] Cong Fang, Chris Junchi Li, Zhouchen Lin, and Tong Zhang. Spider: Near-optimal non-convex optimization via stochastic path-integrated differential es- timator. Advances in Neural Information Processing Sys- tems, 31, 2018.","title":"Spider: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","authors":"Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2021] Hongchang Gao, An Xu, and Heng Huang. On the convergence of communication-efficient local sgd for federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Virtual, pages 18-19, 2021.","title":"On the convergence of communication-efficient local sgd for federated learning","authors":"Gao","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence, Virtual","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gao et al., 2023] Hongchang Gao, My T Thai, and Jie Wu. When decentralized optimization meets federated learn- ing. IEEE Network, 2023.","title":"When decentralized optimization meets federated learning","authors":"Gao","year":"2023","venue":"IEEE Network","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao, 2022] Hongchang Gao. Decentralized stochastic gra- dient descent ascent for finite-sum minimax problems. arXiv preprint arXiv:2212.02724, 2022.","title":"Decentralized stochastic gradient descent ascent for finite-sum minimax problems","authors":"Hongchang Gao, Gao","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goodfellow et al., 2014] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gorbunov et al., 2020] Eduard Gorbunov, Dmitry Kovalev, Dmitry Makarenko, and Peter Richtárik. Linearly con- verging error compensated sgd. Advances in Neural In- formation Processing Systems, 33:20889-20900, 2020.","title":"Linearly converging error compensated sgd","authors":"Gorbunov","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Guo et al., 2020] Zhishuai Guo, Mingrui Liu, Zhuon- ing Yuan, Li Shen, Wei Liu, and Tianbao Yang. Communication-efficient distributed stochastic auc maxi- mization with deep neural networks. In International Con- ference on Machine Learning, pages 3864-3874. PMLR, 2020.","title":"Communication-efficient distributed stochastic auc maximization with deep neural networks","authors":"Guo","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gupta et al., 2021] Vipul Gupta, Dhruv Choudhary, Peter Tang, Xiaohan Wei, Xing Wang, Yuzhen Huang, Arun Ke- jariwal, Kannan Ramchandran, and Michael W Mahoney. Training recommender systems at scale: Communication- efficient model and data parallelism. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 2928-2936, 2021.","title":"Training recommender systems at scale: Communicationefficient model and data parallelism","authors":"Vipul Gupta, Dhruv Choudhary, Peter Tang, Xiaohan Wei, Xing Wang, Yuzhen Huang, Arun Kejariwal, Kannan Ramchandran, Michael W Mahoney","year":"2021","venue":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Haddadpour et al., 2021] Farzin Haddadpour, Moham- mad Mahdi Kamani, Aryan Mokhtari, and Mehrdad Mahdavi. Federated learning with compression: Unified analysis and sharp guarantees. In International Con- ference on Artificial Intelligence and Statistics, pages 2350-2358. PMLR, 2021.","title":"Federated learning with compression: Unified analysis and sharp guarantees","authors":"Farzin Haddadpour, Mohammad Mahdi Kamani, Aryan Mokhtari, Mehrdad Mahdavi","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Huang et al., 2020] Feihu Huang, Shangqian Gao, Jian Pei, and Heng Huang. Accelerated zeroth-order momentum methods from mini to minimax optimization. arXiv preprint arXiv:2008.08170, 3, 2020.","title":"Accelerated zeroth-order momentum methods from mini to minimax optimization","authors":"Huang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ivkin et al., 2019] Nikita Ivkin, Daniel Rothchild, Enayat Ullah, Ion Stoica, Raman Arora, et al. Communication- efficient distributed sgd with sketching. Advances in Neu- ral Information Processing Systems, 32, 2019.","title":"Communicationefficient distributed sgd with sketching","authors":"Nikita Ivkin, Daniel Rothchild, Enayat Ullah, Ion Stoica, Raman Arora","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jiang and Agrawal, 2018] Peng Jiang and Gagan Agrawal. A linear speedup analysis of distributed deep learning with sparse and quantized communication. Advances in Neural Information Processing Systems, 31, 2018.","title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","authors":"Peng Jiang, Gagan Agrawal","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Karimireddy et al., 2019] Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian Stich, and Martin Jaggi. Error feedback fixes signsgd and other gradient compression schemes. In International Conference on Machine Learning, pages 3252-3261. PMLR, 2019.","title":"Error feedback fixes signsgd and other gradient compression schemes","authors":"Praneeth Sai, Quentin Karimireddy, Sebastian Rebjock, Martin Stich, Jaggi","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li and Li, 2022] Xiaoyun Li and Ping Li. Analysis of er- ror feedback in federated non-convex optimization with biased compression. arXiv preprint arXiv:2211.14292, 2022.","title":"Analysis of error feedback in federated non-convex optimization with biased compression","authors":"Li ; Li, Xiaoyun Li, Ping Li","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lin et al., 2020] Tianyi Lin, Chi Jin, and Michael Jordan. On gradient descent ascent for nonconvex-concave mini- max problems. In International Conference on Machine Learning, pages 6083-6093. PMLR, 2020.","title":"On gradient descent ascent for nonconvex-concave minimax problems","authors":"Tianyi Lin, Chi Jin, Michael Jordan","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2019] Mingrui Liu, Zhuoning Yuan, Yiming Ying, and Tianbao Yang. Stochastic auc maxi- mization with deep neural networks. arXiv preprint arXiv:1908.10831, 2019.","title":"Stochastic auc maximization with deep neural networks","authors":"Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Luo et al., 2020] Luo Luo, Haishan Ye, Zhichao Huang, and Tong Zhang. Stochastic recursive gradient descent as- cent for stochastic nonconvex-strongly-concave minimax problems. Advances in Neural Information Processing Systems, 33:20566-20577, 2020.","title":"Stochastic recursive gradient descent ascent for stochastic nonconvex-strongly-concave minimax problems","authors":"Luo Luo, Haishan Ye, Zhichao Huang, Tong Zhang","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Madry et al., 2017] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083, 2017.","title":"Towards deep learning models resistant to adversarial attacks","authors":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Qiu et al., 2019] Han Qiu, Meikang Qiu, and Ruqian Lu. Secure v2x communication network based on intelligent pki and edge computing. IEEE Network, 34(2):172-178, 2019.","title":"Secure v2x communication network based on intelligent pki and edge computing","authors":"Han Qiu, Meikang Qiu, Ruqian Lu","year":"2019","venue":"IEEE Network","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Qiu et al., 2020] Shuang Qiu, Zhuoran Yang, Xiaohan Wei, Jieping Ye, and Zhaoran Wang. Single-timescale stochas- tic nonconvex-concave optimization for smooth nonlinear td learning. arXiv preprint arXiv:2008.10103, 2020.","title":"Single-timescale stochastic nonconvex-concave optimization for smooth nonlinear td learning","authors":"Shuang Qiu, Zhuoran Yang, Xiaohan Wei, Jieping Ye, Zhaoran Wang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Richtárik et al., 2021] Peter Richtárik, Igor Sokolov, and Ilyas Fatkhullin. Ef21: A new, simpler, theoretically bet- ter, and practically faster error feedback. Advances in Neu- ral Information Processing Systems, 34, 2021.","title":"Ef21: A new, simpler, theoretically better, and practically faster error feedback","authors":"Peter Richtárik, Igor Sokolov, Ilyas Fatkhullin","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Rotemberg et al., 2021] Veronica Rotemberg, Nicholas Kurtansky, Brigid Betz-Stablein, Liam Caffery, Em- manouil Chousakos, Noel Codella, Marc Combalia, Stephen Dusza, Pascale Guitera, David Gutman, et al. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Scientific data, 8(1):1-8, 2021.","title":"A patient-centric dataset of images and metadata for identifying melanomas using clinical context","authors":"Veronica Rotemberg, Nicholas Kurtansky, Brigid Betz-Stablein, Liam Caffery, Emmanouil Chousakos, Noel Codella, Marc Combalia, Stephen Dusza, Pascale Guitera, David Gutman","year":"2021","venue":"Scientific data","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Seide et al., 2014] Frank Seide, Hao Fu, Jasha Droppo, Gang Li, and Dong Yu. 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns. In Fifteenth Annual Conference of the In- ternational Speech Communication Association. Citeseer, 2014.","title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns","authors":"Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu","year":"2014","venue":"Fifteenth Annual Conference of the International Speech Communication Association","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Sharma et al., 2022] Pranay Sharma, Rohan Panda, Gauri Joshi, and Pramod Varshney. Federated minimax opti- mization: Improved convergence analyses and algorithms. In International Conference on Machine Learning, pages 19683-19730. PMLR, 2022.","title":"Federated minimax optimization: Improved convergence analyses and algorithms","authors":"Pranay Sharma, Rohan Panda, Gauri Joshi, Pramod Varshney","year":"2022","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Stich et al., 2018] Sebastian U Stich, Jean-Baptiste Cordon- nier, and Martin Jaggi. Sparsified sgd with memory. Advances in Neural Information Processing Systems, 31, 2018.","title":"Sparsified sgd with memory","authors":"Jean-Baptiste Sebastian U Stich, Martin Cordonnier, Jaggi","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Tang et al., 2019] Hanlin Tang, Chen Yu, Xiangru Lian, Tong Zhang, and Ji Liu. Doublesqueeze: Parallel stochas- tic gradient descent with double-pass error-compensated compression. In International Conference on Machine Learning, pages 6155-6165. PMLR, 2019.","title":"Doublesqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","authors":"Hanlin Tang, Chen Yu, Xiangru Lian, Tong Zhang, Ji Liu","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Tarzanagh et al., 2022] Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, and Samet Oymak. Fednest: Federated bilevel, minimax, and com- positional optimization. arXiv preprint arXiv:2205.02215, 2022.","title":"Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, and Samet Oymak. Fednest: Federated bilevel, minimax, and compositional optimization","authors":"Tarzanagh","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wangni et al., 2018] Jianqiao Wangni, Jialei Wang, Ji Liu, and Tong Zhang. Gradient sparsification for communication-efficient distributed optimization. Ad- vances in Neural Information Processing Systems, 31, 2018.","title":"Gradient sparsification for communication-efficient distributed optimization","authors":"Wangni","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wen et al., 2017] Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. Terngrad: Ternary gradients to reduce communication in distributed deep learning. Advances in neural information processing systems, 30, 2017.","title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","authors":"Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Xian et al., 2021] Wenhan Xian, Feihu Huang, Yanfu Zhang, and Heng Huang. A faster decentralized algorithm for nonconvex minimax problems. Advances in Neural In- formation Processing Systems, 34, 2021.","title":"A faster decentralized algorithm for nonconvex minimax problems","authors":"Xian","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Yan et al., 2020] Yan Yan, Yi Xu, Qihang Lin, Wei Liu, and Tianbao Yang. Optimal epoch stochastic gradient descent ascent methods for min-max optimization. Advances in Neural Information Processing Systems, 33:5789-5800, 2020.","title":"Optimal epoch stochastic gradient descent ascent methods for min-max optimization","authors":"Yan Yan, Yi Xu, Qihang Lin, Wei Liu, Tianbao Yang","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Yang et al., 2020] Junchi Yang, Negar Kiyavash, and Niao He. Global convergence and variance-reduced optimiza- tion for a class of nonconvex-nonconcave minimax prob- lems. arXiv preprint arXiv:2002.09621, 2020.","title":"Global convergence and variance-reduced optimization for a class of nonconvex-nonconcave minimax problems","authors":"Yang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Ying et al., 2016] Yiming Ying, Longyin Wen, and Siwei Lyu. Stochastic online auc maximization. Advances in neural information processing systems, 29, 2016.","title":"Stochastic online auc maximization","authors":"Yiming Ying, Longyin Wen, Siwei Lyu","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Yuan et al., 2021] Zhuoning Yuan, Zhishuai Guo, Yi Xu, Yiming Ying, and Tianbao Yang. Federated deep auc max- imization for hetergeneous data with a constant communi- cation complexity. In International Conference on Ma- chine Learning, pages 12219-12229. PMLR, 2021.","title":"Federated deep auc maximization for hetergeneous data with a constant communication complexity","authors":"Yuan","year":"2021","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhang et al., 2020] Jiawei Zhang, Peijun Xiao, Ruoyu Sun, and Zhiquan Luo. A single-loop smoothed gradient descent-ascent algorithm for nonconvex-concave min-max problems. Advances in Neural Information Processing Systems, 33:7377-7389, 2020.","title":"A single-loop smoothed gradient descent-ascent algorithm for nonconvex-concave min-max problems","authors":"Jiawei Zhang, Peijun Xiao, Ruoyu Sun, Zhiquan Luo","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Zhang et al., 2021] Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, and Songtao Lu. Taming communica- tion and sample complexities in decentralized policy eval- uation for cooperative multi-agent reinforcement learn- ing. Advances in Neural Information Processing Systems, 34:18825-18838, 2021.","title":"Taming communication and sample complexities in decentralized policy evaluation for cooperative multi-agent reinforcement learning","authors":"Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, Songtao Lu","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zhang et al., 2023a] Xinwen Zhang, Yihan Zhang, Tianbao Yang, Richard Souvenir, and Hongchang Gao. Feder- ated compositional deep auc maximization. arXiv preprint arXiv:2304.10101, 2023.","title":"Federated compositional deep auc maximization","authors":"Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang et al., 2023b] Yihan Zhang, Wenhao Jiang, Feng Zheng, Chiu C Tan, Xinghua Shi, and Hongchang Gao. Can decentralized stochastic minimax optimization al- gorithms converge linearly for finite-sum nonconvex- nonconcave problems? arXiv preprint arXiv:2304.11788, 2023.","title":"Can decentralized stochastic minimax optimization algorithms converge linearly for finite-sum nonconvexnonconcave problems","authors":"Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zheng et al., 2019] Shuai Zheng, Ziyue Huang, and James Kwok. Communication-efficient distributed blockwise momentum sgd with error-feedback. Advances in Neural Information Processing Systems, 32, 2019.","title":"Communication-efficient distributed blockwise momentum sgd with error-feedback","authors":"Shuai Zheng, Ziyue Huang, James Kwok","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}