{"type":"ScholarlyArticle","title":"Towards Sharper Risk Bounds for Minimax Problems","authors":[{"name":"Bowei Zhu","slug":"bowei-zhu","given":"Bowei","family":"Zhu","affiliation":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China; Beijing Key Laboratory of Big Data Management and Analysis Methods , Beijing , China"},{"name":"Shaojie Li","slug":"shaojie-li","given":"Shaojie","family":"Li","affiliation":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China; Beijing Key Laboratory of Big Data Management and Analysis Methods , Beijing , China"},{"name":"Yong Liu","slug":"yong-liu","given":"Yong","family":"Liu","affiliation":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China; Beijing Key Laboratory of Big Data Management and Analysis Methods , Beijing , China"}],"abstract":"Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds, which are composed by generalization error and optimization error, present 1/n-rates in strongly-convex-strongly-concave (SC-SC) settings. Existing studies mainly focus on minimax problems with specific algorithms for optimization error, with only a few studies on generalization performance, which limit better excess risk bounds. In this paper, we study the generalization bounds measured by the gradients of primal functions using uniform localized convergence. We obtain a sharper high probability generalization error bound for nonconvex-strongly-concave (NC-SC) stochastic minimax problems. Furthermore, we provide dimension-independent results under Polyak-Lojasiewicz condition for the outer layer. Based on our generalization error bound, we analyze some popular algorithms such as empirical saddle point (ESP), gradient descent ascent (GDA) and stochastic gradient descent ascent (SGDA). We derive better excess primal risk bounds with further reasonable assumptions, which, to the best of our knowledge, are n times faster than exist results in minimax problems.","doi":"10.24963/ijcai.2024/630","url":"https://ijcai.org/proceedings/2024/630","pdf":"https://ijcai.org/proceedings/2024/0630.pdf","markdown":"https://ijcai.org/proceedings/2024/630.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/630","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":630,"pages":{"first":5698,"last":5706},"keywords":["Machine Learning: ML: Robustness","Machine Learning: ML: Learning theory","Machine Learning: ML: Reinforcement learning","Machine Learning: ML: Adversarial machine learning"],"videos":[],"references":[{"position":1,"raw":"[Allen-Zhu et al., 2019] Zeyuan Allen-Zhu, Yuanzhi Li, and Zhao Song. A convergence theory for deep learning via over- parameterization. In ICML, 2019.","title":"A convergence theory for deep learning via overparameterization","authors":"Allen-Zhu","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arora et al., 2018] Sanjeev Arora, Nadav Cohen, Noah Golowich, and Wei Hu. A convergence analysis of gradient descent for deep linear neural networks. arXiv preprint arXiv:1810.02281, 2018.","title":"A convergence analysis of gradient descent for deep linear neural networks","authors":"Sanjeev Arora, Nadav Cohen, Noah Golowich, Wei Hu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bartlett et al., 2002] Peter L Bartlett, Olivier Bousquet, and Sha- har Mendelson. Localized rademacher complexities. In Inter- national Conference on Computational Learning Theory, pages 44-58. Springer, 2002.","title":"Localized rademacher complexities","authors":"Olivier Peter L Bartlett, Shahar Bousquet, Mendelson","year":"2002","venue":"International Conference on Computational Learning Theory","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bassily et al., 2020] Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, and Kunal Talwar. Stability of stochastic gradient de- scent on nonsmooth convex losses. In NeurIPS, 2020.","title":"Stability of stochastic gradient descent on nonsmooth convex losses","authors":"Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, Kunal Talwar","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Boucheron et al., 2013] Stéphane Boucheron, Gábor Lugosi, and Pascal Massart. Concentration inequalities: A nonasymptotic theory of independence. Oxford university press, 2013.","title":"Concentration inequalities: A nonasymptotic theory of independence","authors":"Stéphane Boucheron, Gábor Lugosi, Pascal Massart","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bousquet and Elisseeff, 2002] Olivier Bousquet and André Elisse- eff. Stability and generalization. The Journal of Machine Learn- ing Research, 2:499-526, 2002.","title":"Stability and generalization","authors":"Elisseeff Bousquet, Olivier Bousquet, André Elisseeff","year":"2002","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bousquet et al., 2020] Olivier Bousquet, Yegor Klochkov, and Nikita Zhivotovskiy. Sharper bounds for uniformly stable algo- rithms. In Conference on Learning Theory, 2020.","title":"Sharper bounds for uniformly stable algorithms","authors":"Bousquet","year":"2020","venue":"Conference on Learning Theory","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Charles and Papailiopoulos, 2018] Zachary Charles and Dimitris Papailiopoulos. Stability and generalization of learning algo- rithms that converge to global optima. In ICML, 2018.","title":"Stability and generalization of learning algorithms that converge to global optima","authors":"Zachary Charles, Dimitris Papailiopoulos","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Chen et al., 2017] Robert S Chen, Brendan Lucier, Yaron Singer, and Vasilis Syrgkanis. Robust optimization for non-convex ob- jectives. NeurIPS, 2017.","title":"Robust optimization for non-convex objectives","authors":"Brendan Robert S Chen, Yaron Lucier, Vasilis Singer, Syrgkanis","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dai et al., 2018] Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, and Le Song. Sbeed: Convergent reinforcement learning with nonlinear function approximation. In ICML, 2018.","title":"Sbeed: Convergent reinforcement learning with nonlinear function approximation","authors":"Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Davis and Drusvyatskiy, 2022] Damek Davis and Dmitriy Drusvy- atskiy. Graphical convergence of subgradients in nonconvex op- timization and learning. Mathematics of Operations Research, 47(1):209-231, 2022.","title":"Damek Davis and Dmitriy Drusvyatskiy. Graphical convergence of subgradients in nonconvex optimization and learning","authors":"Drusvyatskiy Davis","year":"2022","venue":"Mathematics of Operations Research","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dirksen, 2015] Sjoerd Dirksen. Tail bounds via generic chaining. Electronic Journal of Probability, 20:1-29, 2015.","title":"Tail bounds via generic chaining","authors":"Sjoerd Dirksen","year":"2015","venue":"Electronic Journal of Probability","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Du et al., 2017] Simon S Du, Jianshu Chen, Lihong Li, Lin Xiao, and Dengyong Zhou. Stochastic variance reduction methods for policy evaluation. In ICML, 2017.","title":"Stochastic variance reduction methods for policy evaluation","authors":"Jianshu Simon S Du, Lihong Chen, Lin Li, Dengyong Xiao, Zhou","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Du et al., 2018] Simon S Du, Xiyu Zhai, Barnabas Poc- zos, and Aarti Singh. Gradient descent provably opti- mizes over-parameterized neural networks. arXiv preprint arXiv:1810.02054, 2018.","title":"Gradient descent provably optimizes over-parameterized neural networks","authors":"Xiyu Simon S Du, Barnabas Zhai, Aarti Poczos, Singh","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Farnia and Ozdaglar, 2021] Farzan Farnia and Asuman Ozdaglar. Train simultaneously, generalize better: Stability of gradient- based minimax learners. In ICML, 2021.","title":"Train simultaneously, generalize better: Stability of gradientbased minimax learners","authors":"Farzan Farnia, Asuman Ozdaglar","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Feldman and Vondrak, 2018] Vitaly Feldman and Jan Vondrak. Generalization bounds for uniformly stable algorithms. NeurIPS, 31, 2018.","title":"Generalization bounds for uniformly stable algorithms","authors":"Vitaly Feldman, Jan Vondrak","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Feldman and Vondrak, 2019] Vitaly Feldman and Jan Vondrak. High probability generalization bounds for uniformly stable al- gorithms with nearly optimal rate. In Conference on Learning Theory, 2019.","title":"High probability generalization bounds for uniformly stable algorithms with nearly optimal rate","authors":"Vitaly Feldman, Jan Vondrak","year":"2019","venue":"Conference on Learning Theory","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Fisher, 1922] Ronald A Fisher. On the mathematical foundations of theoretical statistics. Philosophical transactions of the Royal Society of London. Series A, containing papers of a mathematical or physical character, 222(594-604):309-368, 1922.","title":"On the mathematical foundations of theoretical statistics","authors":"Ronald A Fisher","year":"1922","venue":"Philosophical transactions of the Royal Society of London. Series A, containing papers of a mathematical or physical character","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Goodfellow et al., 2016] Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. Deep learning, volume 1. MIT Press, 2016.","title":"Deep learning","authors":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, Yoshua Bengio","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Guo et al., 2020] Zhishuai Guo, Yan Yan, Zhuoning Yuan, and Tianbao Yang. Fast objective & duality gap convergence for nonconvex-strongly-concave min-max problems. arXiv preprint arXiv:2006.06889, 2020.","title":"Fast objective & duality gap convergence for nonconvex-strongly-concave min-max problems","authors":"Guo","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Hardt and Ma, 2016] Moritz Hardt and Tengyu Ma. Identity mat- ters in deep learning. arXiv preprint arXiv:1611.04231, 2016.","title":"Identity matters in deep learning","authors":"Ma ; Hardt, Moritz Hardt, Tengyu Ma","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Hsieh et al., 2019] Yu-Guan Hsieh, Franck Iutzeler, Jérôme Mal- ick, and Panayotis Mertikopoulos. On the convergence of single- call stochastic extra-gradient methods. NeurIPS, 2019.","title":"On the convergence of singlecall stochastic extra-gradient methods","authors":"Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Karimi et al., 2016] Hamed Karimi, Julie Nutini, and Mark Schmidt. Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition. In ECML, pages 795-811. Springer, 2016.","title":"Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition","authors":"Hamed Karimi, Julie Nutini, Mark Schmidt","year":"2016","venue":"ECML","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Kleywegt et al., 2002] Anton J Kleywegt, Alexander Shapiro, and Tito Homem-de Mello. The sample average approximation method for stochastic discrete optimization. SIAM Journal on optimization, 12(2):479-502, 2002.","title":"The sample average approximation method for stochastic discrete optimization","authors":"Anton J Kleywegt, Alexander Shapiro, Tito Homem, -De Mello","year":"2002","venue":"SIAM Journal on optimization","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Klochkov and Zhivotovskiy, 2021] Yegor Klochkov and Nikita Zhivotovskiy. Stability and deviation optimal risk bounds with convergence rate o(1/n). NeurIPS, 2021.","title":"Yegor Klochkov and Nikita Zhivotovskiy. Stability and deviation optimal risk bounds with convergence rate o(1/n)","authors":"Zhivotovskiy Klochkov","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Kuzborskij and Lampert, 2018] Ilja Kuzborskij and Christoph Lampert. Data-dependent stability of stochastic gradient descent. In ICML, 2018.","title":"Data-dependent stability of stochastic gradient descent","authors":"Lampert Kuzborskij, Ilja Kuzborskij, Christoph Lampert","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lei and Ying, 2020] Yunwen Lei and Yiming Ying. Fine-grained analysis of stability and generalization for stochastic gradient de- scent. In ICML, 2020.","title":"Yunwen Lei and Yiming Ying. Fine-grained analysis of stability and generalization for stochastic gradient descent","authors":"Ying Lei","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Lei et al., 2021] Yunwen Lei, Zhenhuan Yang, Tianbao Yang, and Yiming Ying. Stability and generalization of stochastic gradient methods for minimax problems. In ICML, 2021.","title":"Stability and generalization of stochastic gradient methods for minimax problems","authors":"Lei","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Li and Liang, 2018] Yuanzhi Li and Yingyu Liang. Learning over- parameterized neural networks via stochastic gradient descent on structured data. NeurIPS, 2018.","title":"Learning overparameterized neural networks via stochastic gradient descent on structured data","authors":"Li, Liang ; ] Yuanzhi Li, Yingyu Liang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Li and Liu, 2021a] Shaojie Li and Yong Liu. High probability generalization bounds with fast rates for minimax problems. In ICLR, 2021.","title":"High probability generalization bounds with fast rates for minimax problems","authors":"Li, Liu, Shaojie Li, Yong Liu","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Li and Liu, 2021b] Shaojie Li and Yong Liu. Improved learning rates for stochastic optimization: Two theoretical viewpoints. arXiv preprint arXiv:2107.08686, 2021.","title":"Improved learning rates for stochastic optimization: Two theoretical viewpoints","authors":"Li, Liu, Shaojie Li, Yong Liu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Lin et al., 2020] Tianyi Lin, Chi Jin, and Michael Jordan. On gra- dient descent ascent for nonconvex-concave minimax problems. In ICML, 2020.","title":"On gradient descent ascent for nonconvex-concave minimax problems","authors":"Tianyi Lin, Chi Jin, Michael Jordan","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Liu et al., 2017] Tongliang Liu, Gábor Lugosi, Gergely Neu, and Dacheng Tao. Algorithmic stability and hypothesis complexity. In ICML, 2017.","title":"Algorithmic stability and hypothesis complexity","authors":"Liu","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Liu et al., 2018] Mingrui Liu, Xiaoxuan Zhang, Lijun Zhang, Rong Jin, and Tianbao Yang. Fast rates of erm and stochastic approximation: Adaptive to error bound conditions. NeurIPS, 2018.","title":"Fast rates of erm and stochastic approximation: Adaptive to error bound conditions","authors":"Mingrui Liu, Xiaoxuan Zhang, Lijun Zhang, Rong Jin, Tianbao Yang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Liu et al., 2021] Mingrui Liu, Hassan Rafique, Qihang Lin, and Tianbao Yang. First-order convergence theory for weakly- convex-weakly-concave min-max problems. The Journal of Ma- chine Learning Research, 22(1):7651-7684, 2021.","title":"First-order convergence theory for weaklyconvex-weakly-concave min-max problems","authors":"Liu","year":"2021","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Loizou et al., 2020] Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, and Ioannis Mitliagkas. Stochastic hamiltonian gradient methods for smooth games. In ICML, 2020.","title":"Stochastic hamiltonian gradient methods for smooth games","authors":"Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau, Pascal Vincent, Simon Lacoste-Julien, Ioannis Mitliagkas","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[London et al., 2016] Ben London, Bert Huang, and Lise Getoor. Stability and generalization in structured prediction. The Journal of Machine Learning Research, 17(1):7808-7859, 2016.","title":"Stability and generalization in structured prediction","authors":"London","year":"2016","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Luo et al., 2020] Luo Luo, Haishan Ye, Zhichao Huang, and Tong Zhang. Stochastic recursive gradient descent ascent for stochastic nonconvex-strongly-concave minimax problems. NeurIPS, 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":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Mei et al., 2018] Song Mei, Yu Bai, and Andrea Montanari. The landscape of empirical risk for nonconvex losses. The Annals of Statistics, 46(6A):2747-2774, 2018.","title":"The landscape of empirical risk for nonconvex losses","authors":"Song Mei, Yu Bai, Andrea Montanari","year":"2018","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Namkoong and Duchi, 2017] Hongseok Namkoong and John C Duchi. Variance-based regularization with convex objectives. NeurIPS, 2017.","title":"Variance-based regularization with convex objectives","authors":"Duchi Namkoong, Hongseok Namkoong, John C Duchi","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Nedić and Ozdaglar, 2009] Angelia Nedić and Asuman Ozdaglar. Subgradient methods for saddle-point problems. Journal of opti- mization theory and applications, 142:205-228, 2009.","title":"Subgradient methods for saddle-point problems","authors":"Angelia Nedić, Asuman Ozdaglar","year":"2009","venue":"Journal of optimization theory and applications","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Nemirovski et al., 2009] Arkadi Nemirovski, Anatoli Juditsky, Guanghui Lan, and Alexander Shapiro. Robust stochastic ap- proximation approach to stochastic programming. SIAM Journal on optimization, 19(4):1574-1609, 2009.","title":"Robust stochastic approximation approach to stochastic programming","authors":"Arkadi Nemirovski, Anatoli Juditsky, Guanghui Lan, Alexander Shapiro","year":"2009","venue":"SIAM Journal on optimization","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Nesterov, 2003] Yurii Nesterov. Introductory lectures on convex optimization: A basic course, volume 87. Springer Science & Business Media, 2003.","title":"Introductory lectures on convex optimization: A basic course","authors":"Yurii Nesterov","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Nouiehed et al., 2019] Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D Lee, and Meisam Razaviyayn. Solving a class of non-convex min-max games using iterative first order methods. NeurIPS, 32, 2019.","title":"Solving a class of non-convex min-max games using iterative first order methods","authors":"Maziar Maher Nouiehed, Tianjian Sanjabi, Jason D Huang, Meisam Lee, Razaviyayn","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Ozdaglar et al., 2022] Asuman Ozdaglar, Sarath Pattathil, Jiawei Zhang, and Kaiqing Zhang. What is a good metric to study gener- alization of minimax learners? arXiv preprint arXiv:2206.04502, 2022.","title":"What is a good metric to study generalization of minimax learners","authors":"Asuman Ozdaglar, Sarath Pattathil, Jiawei Zhang, Kaiqing Zhang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Palaniappan and Bach, 2016] Balamurugan Palaniappan and Fran- cis Bach. Stochastic variance reduction methods for saddle-point problems. NeurIPS, 2016.","title":"Stochastic variance reduction methods for saddle-point problems","authors":"Balamurugan Palaniappan, Francis Bach","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Pinelis, 1994] Iosif Pinelis. Optimum bounds for the distributions of martingales in banach spaces. The Annals of Probability, pages 1679-1706, 1994.","title":"Optimum bounds for the distributions of martingales in banach spaces","authors":"Iosif Pinelis","year":"1994","venue":"The Annals of Probability","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Rafique et al., 2022] Hassan Rafique, Mingrui Liu, Qihang Lin, and Tianbao Yang. Weakly-convex-concave min-max optimiza- tion: provable algorithms and applications in machine learning. Optimization Methods and Software, 37(3):1087-1121, 2022.","title":"Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning","authors":"Hassan Rafique, Mingrui Liu, Qihang Lin, Tianbao Yang","year":"2022","venue":"Optimization Methods and Software","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Rogers and Wagner, 1978] William H Rogers and Terry J Wagner. A finite sample distribution-free performance bound for local dis- crimination rules. The Annals of Statistics, pages 506-514, 1978.","title":"A finite sample distribution-free performance bound for local discrimination rules","authors":"Rogers, Wagner ; William, H Rogers, Terry J Wagner","year":"1978","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Shalev-Shwartz et al., 2010] Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, and Karthik Sridharan. Learnability, stability and uniform convergence. The Journal of Machine Learning Re- search, 11:2635-2670, 2010.","title":"Learnability, stability and uniform convergence","authors":"Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan","year":"2010","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Smale and Zhou, 2007] Steve Smale and Ding-Xuan Zhou. Learn- ing theory estimates via integral operators and their approxima- tions. Constructive approximation, 26(2):153-172, 2007.","title":"Learning theory estimates via integral operators and their approximations","authors":"Zhou Smale, Steve Smale, Ding-Xuan Zhou","year":"2007","venue":"Constructive approximation","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Srebro et al., 2010] Nathan Srebro, Karthik Sridharan, and Ambuj Tewari. Optimistic rates for learning with a smooth loss. arXiv preprint arXiv:1009.3896, 2010.","title":"Optimistic rates for learning with a smooth loss","authors":"Nathan Srebro, Karthik Sridharan, Ambuj Tewari","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Talagrand, 1996] Michel Talagrand. Majorizing measures: the generic chaining. The Annals of Probability, 24(3):1049-1103, 1996.","title":"Majorizing measures: the generic chaining","authors":"Michel Talagrand","year":"1996","venue":"The Annals of Probability","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Tarres and Yao, 2014] Pierre Tarres and Yuan Yao. Online learning as stochastic approximation of regularization paths: Optimality and almost-sure convergence. IEEE Transactions on Information Theory, 60(9):5716-5735, 2014.","title":"Online learning as stochastic approximation of regularization paths: Optimality and almost-sure convergence","authors":"Yao Tarres, Pierre Tarres, Yuan Yao","year":"2014","venue":"IEEE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Thekumparampil et al., 2019] Kiran K Thekumparampil, Prateek Jain, Praneeth Netrapalli, and Sewoong Oh. Efficient algorithms for smooth minimax optimization. NeurIPS, 2019.","title":"Efficient algorithms for smooth minimax optimization","authors":"Prateek Kiran K Thekumparampil, Praneeth Jain, Sewoong Netrapalli, Oh","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Van der Vaart, 2000] Aad W Van der Vaart. Asymptotic statistics, volume 3. Cambridge university press, 2000.","title":"Asymptotic statistics","authors":"W Aad, Van Der, Vaart","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Vapnik, 1999] Vladimir N Vapnik. An overview of statisti- cal learning theory. IEEE transactions on neural networks, 10(5):988-999, 1999.","title":"An overview of statistical learning theory","authors":"N Vladimir, Vapnik","year":"1999","venue":"IEEE transactions on neural networks","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Wainwright, 2019] Martin J Wainwright. High-dimensional statis- tics: A non-asymptotic viewpoint, volume 48. Cambridge univer- sity press, 2019.","title":"High-dimensional statistics: A non-asymptotic viewpoint","authors":"Wainwright Martin","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Xu and Zeevi, 2020] Yunbei Xu and Assaf Zeevi. Towards opti- mal problem dependent generalization error bounds in statistical learning theory. arXiv preprint arXiv:2011.06186, 2020.","title":"Towards optimal problem dependent generalization error bounds in statistical learning theory","authors":"Zeevi Xu, Yunbei Xu, Assaf Zeevi","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Yan et al., 2020] Yan Yan, Yi Xu, Qihang Lin, Wei Liu, and Tian- bao Yang. Optimal epoch stochastic gradient descent ascent methods for min-max optimization. NeurIPS, 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":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Yang et al., 2020] Junchi Yang, Negar Kiyavash, and Niao He. Global convergence and variance reduction for a class of nonconvex-nonconcave minimax problems. NeurIPS, 33:1153- 1165, 2020.","title":"Global convergence and variance reduction for a class of nonconvex-nonconcave minimax problems","authors":"Yang","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":62,"raw":"[Zhang and Zhou, 2019] Lijun Zhang and Zhi-Hua Zhou. Stochas- tic approximation of smooth and strongly convex functions: Be- yond the o(1/t) convergence rate. In Conference on Learning Theory, 2019.","title":"Stochastic approximation of smooth and strongly convex functions: Beyond the o(1/t) convergence rate","authors":"Lijun Zhang, Zhi-Hua Zhou","year":"2019","venue":"Conference on Learning Theory","doi":null,"url":null,"internal_url":null},{"position":63,"raw":"[Zhang et al., 2017] Lijun Zhang, Tianbao Yang, and Rong Jin. Empirical risk minimization for stochastic convex optimization: o(1/n)-and o(1/n 2 )-type of risk bounds. In Conference on Learning Theory, 2017.","title":"Empirical risk minimization for stochastic convex optimization: o(1/n)-and o(1/n 2 )-type of risk bounds","authors":"Lijun Zhang, Tianbao Yang, Rong Jin","year":"2017","venue":"Conference on Learning Theory","doi":null,"url":null,"internal_url":null},{"position":64,"raw":"[Zhang et al., 2021] Junyu Zhang, Mingyi Hong, Mengdi Wang, and Shuzhong Zhang. Generalization bounds for stochastic sad- dle point problems. In International Conference on Artificial In- telligence and Statistics, pages 568-576. PMLR, 2021.","title":"Generalization bounds for stochastic saddle point problems","authors":"Zhang","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":65,"raw":"[Zhang et al., 2022] Siqi Zhang, Yifan Hu, Liang Zhang, and Niao He. Uniform convergence and generalization for nonconvex stochastic minimax problems. arXiv preprint arXiv:2205.14278, 2022.","title":"Uniform convergence and generalization for nonconvex stochastic minimax problems","authors":"Siqi Zhang, Yifan Hu, Liang Zhang, Niao He","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}