## Papers## PreprintsH. Dahal, W. Liu, **Y. Xu**. Damped Proximal Augmented Lagrangian Method for weakly-Convex Problems with Convex Constraints. Submitted, 2023. [arXiv]W. Liu, Q. Lin, **Y Xu**. First-order Methods for Affinely Constrained Composite Non-convex Non-smooth Problems: Lower Complexity Bound and Near-optimal Methods. Submitted, 2023. [arXiv]G. Mancino-Ball and **Y. Xu**. Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems. Submitted, 2023. [arXiv]X. Zhang, G. Mancino-Ball, NS Aybat, **Y. Xu**. Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization. Submitted, 2023. [arXiv]Y. Xu. Decentralized gradient descent maximization method for composite nonconvex strongly-concave minimax problems. Accepted in SIAM Journal on Optimization. [arXiv] Z. Li, P. Chen, S. Liu, S. Lu, **Y. Xu**. Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization. Accepted in Computational Optimization and Applications. [arXiv]N. Zhou, K. Choi, B. Chen, Y. Du, J. Liu, **Y. Xu**. Correntropy-Based Low-Rank Matrix Factorization With Constraint Graph Learning for Image Clustering.*IEEE Transactions on Neural Networks and Learning Systems*. [online first]
## 2023Y. Yan, J. Chen, P. Chen, X. Cui, S. Lu, **Y. Xu**. Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data.*Proceedings of the 40th International Conference on Machine Learning*, PMLR 202:39035–39061, 2023. [arXiv]G. Mancino-Ball, **Y. Xu**, J. Chen. A Decentralized Primal-Dual Framework for Non-convex Smooth Consensus Optimization.*IEEE Transactions on Signal Processing*, 71, 525–538, 2023. [arXiv]N. Zhou, H. Qin, KS Choi, Y. Du, J. Liu, P. Li, X. Huang, K. Chi, **Y. Xu**. Correntropy based model predictive controller with multi-constraints for robust path trajectory tracking of self-driving vehicle. Journal of the Franklin Institute, 360(10), 6929–6952, 2023.G. Mancino-Ball, S. Miao, **Y. Xu**, J. Chen. Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization. AAAI, 37(7), 9055–9063, 2023. [arXiv]J. Zhang, H. Chao, A. Dhurandhar, P.Y. Chen, A. Tajer, **Y. Xu**, P. Yan. When Neural Networks Fail to Generalize? A Model Sensitivity Perspective. AAAI, 37(9), 11219–11227, 2023. [arXiv]Q. Lin and **Y. Xu**. Reducing the complexity of two classes of optimization problems by inexact accelerated proximal gradient method.*SIAM Journal on Optimization*, 33(1), 1–35, 2023. [pdf] [arXiv longer version]**Yangyang Xu**and Yibo Xu. Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization.*Journal of Optimization Theory and Applications*, 196, 266–297, 2023. [arXiv] [published version]**Yangyang Xu**, Yibo Xu, Y. Yan, C. Sutcher-Shepard, L. Grinberg and J. Chen. Parallel and distributed asynchronous adaptive stochastic gradient methods.*Mathematical Programming Computation*, 15, 471–508, 2023. [arXiv] [published version]
## 2022**Y. Xu**. First-order methods for problems with O(1) functional constraints can have almost the same convergence rate as for unconstrained problems.*SIAM Journal on Optimization*, 32(3), 1759–1790, 2022. [pdf] [arXiv]Q. Lin, R. Ma and **Y. Xu**. Complexity of an inexact proximal-point penalty method for constrained smooth non-convex optimization,*Computational Optimization and Applications*, 82, 175–224, 2022. [published version] [arXiv]**Yangyang Xu**, Yibo Xu, Y. Yan, and J. Chen. Distributed stochastic inertial-accelerated methods with delayed derivatives for nonconvex problems.*SIAM Journal on Imaging Sciences*, 15(2):550–590, 2022. [pdf]Y. Yan and **Y. Xu**. Adaptive Primal-Dual Stochastic Gradient Method for Expectation-constrained Convex Stochastic Programs.*Mathematical Programming Computation*, 14, 319–363, 2022. [published version] [arXiv]Z. Li, P. Chen, S. Liu, S. Lu, **Y. Xu**. Zeroth-order Optimization for Composite Problems with Functional Constraints.*AAAI*, 36(7), 7453–7461, 2022. [arXiv]
## 2021Yibo Xu and **Yangyang Xu**. Katyusha Acceleration for Convex Finite-Sum Compositional Optimization.*INFORMS Journal on Optimization*, 3(4):418–443, 2021. [arXiv]Z. Li, P. Chen, S. Liu, S. Lu, **Y. Xu**. Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization.*AISTATS*, 130, 2170–2178, 2021. [arXiv]Z. Li and **Y. Xu**. Augmented Lagrangian based first-order methods for convex-constrained programs with weakly-convex objective.*INFORMS Journal on Optimization*, 3(4):373-397, 2021. [arXiv]**Y. Xu**. Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming.*Mathematical Programming, Series A*, 185, 199–244, 2021. [published version] [arXiv]Y. Ouyang and **Y. Xu**. Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems.*Mathematical Programming, Series A*, 185, 1–35, 2021. [published version] [arXiv]**Y. Xu**. First-order methods for constrained convex programming based on linearized augmented Lagrangian function.*INFORMS Journal on Optimization*, 3(1), 89–117, 2021. [published version]
## 2020**Y. Xu**. Primal-dual stochastic gradient method for convex programs with many functional constraints.*SIAM Journal on Optimization*, 30(2), 1664–1692, 2020. [arXiv] [Slides]N. Zhou, B. Chen, T. Jiang, Y. Du and **Y. Xu**. Maximum Correntropy Criterion based Robust Semi-supervised Concept Factorization for Image Representation.*IEEE Transactions on Neural Networks and Learning Systems*, 31(10), 3877–3891, 2020.C. Wu and **Y. Xu**. Greedy coordinate descent method on non-negative quadratic programming.*2020 IEEE 11th Sensor Array and Multichannel Signal Processing Workshop (SAM)*, pp. 1–5. [arXiv]T. Sun, Y. Sun, **Y. Xu**and W. Yin. Markov Chain Block coordinate descent.*Computational Optimization and Applications*, 75(1), 35–61, 2020. [published version] [arXiv]
## 2019X. Gao, **Y. Xu**and S. Zhang. Randomized primal-dual proximal block coordinate updates.*Journal of the Operations Research Society of China*, 7(2), pp. 205–250, 2019. [arXiv]**Y. Xu**. Asynchronous parallel primal-dual block coordinate update methods for affinely constrained convex programs.*Computational Optimization and Applications*, 72(1), pp. 87–113, 2019. [arXiv] [Slides]Z. Peng, **Y. Xu**, M. Yan and W. Yin. On the Convergence of Asynchronous Parallel Iteration with Unbounded Delays. Special issue on*Journal of the Operations Research Society of China*, 7(1), pp. 5–42, 2019. [pdf]N. Zhou, **Y. Xu**, H. Chen, Z. Yuan and B. Chen. Maximum Correntropy Criterion based Sparse Subspace Learning for Unsupervised Feature Selection.*IEEE Transactions on Circuits and Systems for Video Technology*, 29(2), pp. 404–417, 2019.
## 2018D. Oliveira, H. Wolkowicz and **Y. Xu**. ADMM for the SDP relaxation of the QAP.*Mathematical Programming Computation*, 10(4), pp. 631–658, 2018. [code and more] [arXiv]B. Liu, T. Xie, **Y. Xu**, M. Ghavamzadeh, Y. Chow, D. Lyu and D. Yoon. A Block Coordinate Ascent Algorithm for Mean-Variance Optimization, NeurIPS, pp. 1073–1083, 2018.X. Li, J. Ren, S. Rambhatla, **Y. Xu**and J. Haupt. Robust PCA via dictionary based outlier pursuit, ICASSP, pp. 4699–4703, 2018.**Y. Xu**. Hybrid Jacobian and Gauss-Seidel proximal block coordinate update methods for linearly constrained convex programming.*SIAM Journal on Optimization*, 28(1), pp. 646–670, 2018. [pdf]Y. Chen, J. Zhang and **Y. Xu**. Adaptive lasso for accelerated hazards models.*Journal of Statistical Computation and Simulation*, 88(15), pp. 2948–2960, 2018.**Y. Xu**and S. Zhang. Accelerated Primal-Dual Proximal Block Coordinate Updating Methods for Constrained Convex Optimization.*Computational Optimization and Applications*, 70(1), 91–128, 2018. [arXiv]**Y. Xu**. On the convergence of higher-order orthogonality iteration.*Linear and Multilinear Algebra*, 66(11), pp. 2247–2265, 2018. [arXiv] [Slides]F. Wen and **Y. Xu**. HOSVD Based Multidimensional Parameter Estimation for Massive MIMO System from Incomplete Channel Measurements.*Multidimensional Systems and Signal Processing*, 29(4), pp. 1255–1267, 2018.
## 2017**Y. Xu**. Accelerated first-order primal-dual proximal methods for linearly constrained composite convex programming.*SIAM Journal on Optimization*, 27(3), 1459–1484, 2017. [pdf]**Y. Xu**and W. Yin. A globally convergent algorithm for nonconvex optimization based on block coordinate update.*Journal of Scientific Computing*, 72(2), 700–734, 2017. [arXiv]**Y. Xu**. Fast algorithms for higher-order singular value decomposition from incomplete data.*Journal of Computational Mathematics, Special Issues on Optimization and Structured Solution*, 35(4), 395–420, 2017. [arXiv] [code]
## 2016 and earlierZ. Peng, **Y. Xu**, M. Yan and W. Yin. ARock: an algorithmic framework for asynchronous parallel coordinate updates.*SIAM Journal on Scientific Computing*, 38(5), A2851–A2879, 2016. [arXiv] [code and more]Z. Peng, T. Wu, **Y. Xu**, M. Yan and W. Yin. Coordinate Friendly Structures, Algorithms and applications.*Annals of Mathematical Sciences and Applications*, 1(1), pp. 57–119, 2016. [arXiv]**Y. Xu**and W. Yin. A fast patch-dictionary method for whole image recovery.*Inverse Problems and Imaging*, 10(2), 563–583, 2016. [code and more] [arXiv]N. Zhou, **Y. Xu**, H. Cheng, J. Fang and W. Pedrycz. Global and local structure preserving sparse subspace learning: an iterative approach to unsupervised feature selection.*Pattern Recognition*, 53, pp. 87–101, 2016. [arXiv]
**Y. Xu**and W. Yin. Block stochastic gradient iteration for convex and nonconvex optimization.*SIAM Journal on Optimization*, 25(3), 1686–1716, 2015. [pdf] [Slides]**Y. Xu**, R. Hao, W. Yin and Z. Su. Parallel matrix factorization for low-rank tensor completion.*Inverse Problems and Imaging*, 9(2), 601–624, 2015. [pdf] [code]**Y. Xu**. Alternating proximal gradient method for sparse nonnegative Tucker decomposition.*Mathematical Programming Computation*, 7(1), 39–70, 2015. [code]**Y. Xu**, I. Akrotirianakis and A. Chakraborty. Proximal gradient method for huberized support vector machine,*Pattern Analysis and Applications*, 19(4), 989–1005, 2015. [pdf]**Y. Xu**, I. Akrotirianakis and A. Chakraborty. Alternating direction method of multipliers for regularized multiclass support vector machines.*International Workshop on Machine Learning, Optimization and Big Data*, 105–117, 2015. [arXiv]
**Y. Xu**, W. Yin and S. Osher. Learning circulant sensing kernels.*Inverse Problems and Imaging*8(3), 901–923, 2014. [paper][code and more]
**Y. Xu**and W. Yin. A block coordinate descent method for regularized multi-convex optimization with applications to nonnegative tensor factorization and completion.*SIAM Journal on imaging sciences*, 6(3), pp. 1758–1789, 2013. [code and more]M. Lai, **Y. Xu**and W. Yin. Improved iteratively reweighted least squares for unconstrained smoothed Lq minimization.*SIAM Journal on Numerical Analysis*, 51(2), pp. 927–957, 2013. [code]
Q. Ling, **Y. Xu**, W. Yin and Z. Wen. Distributed low-rank matrix completion. (ICASSP), pp. 2925–2928, 2012.**Y. Xu**and J. Cui. Multitask n-Vehicle Exploration Problem: complexity and algorithms.*Journal of Systems Science and Complexity*, pp. 1080–1092, 2012.
**Y. Xu**, W. Yin, Z. Wen and Y. Zhang. An alternating direction algorithm for matrix completion with nonnegative factors.*Journal of Frontiers of Mathematics in China, Special Issues on Computational Mathematics*(Springer), pp. 365–384, 2011. [code] [arXiv]
## Technical Reports |