Augmented Lagrangian–Based First-Order Methods for Convex-Constrained Programs with Weakly Convex Objective

References

• Aybat NS, Iyengar G (2013) An augmented Lagrangian method for conic convex programming. Preprint, submitted February 26, https://arxiv.org/abs/1302.6322.Google Scholar
• Boob D, Deng Q, Lan G (2019) Stochastic first-order methods for convex and nonconvex functional constrained optimization. Preprint, submitted August 7, https://arxiv.org/abs/1908.02734.Google Scholar
• Hamedani EY, Aybat NS (2018) A primal-dual algorithm for general convex-concave saddle point problems. Preprint, submitted March 4, https://dev.arxiv.org/abs/1803.01401v1.Google Scholar
• Hestenes MR (1969) Multiplier and gradient methods. J. Optim. Theory Appl. 4(5):303–320.Google Scholar
• Kong W, Melo JG, Monteiro RD (2019) Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs. SIAM J. Optim. 29(4):2566–2593.Google Scholar
• Lan G, Monteiro RD (2013) Iteration-complexity of first-order penalty methods for convex programming. Math. Programming 138(1-2):115–139.Google Scholar
• Lan G, Monteiro RD (2016) Iteration-complexity of first-order augmented Lagrangian methods for convex programming. Math. Programming155(1-2):511–547.Google Scholar
• Li F, Qu Z (2019) An inexact proximal augmented Lagrangian framework with arbitrary linearly convergent inner solver for composite convex optimization. Preprint, submitted September 20, https://arxiv.org/abs/1909.09582.Google Scholar
• Li Z, Xu Y (2020) Augmented Lagrangian based first-order methods for convex and nonconvex programs: Nonergodic convergence and iteration complexity. Preprint, submitted March 19, https://arxiv.org/abs/2003.08880v1.Google Scholar
• Lin Q, Xiao L (2014) An adaptive accelerated proximal gradient method and its homotopy continuation for sparse optimization. Proc. Machine Learn. Res. 32(1):73–81.Google Scholar
• Lin Q, Ma R, Xu Y (2019) Inexact proximal-point penalty methods for non-convex optimization with non-convex constraints. Preprint, submitted August 30, https://arxiv.org/abs/1908.11518v1.Google Scholar
• Liu Y-F, Liu X, Ma S (2019) On the nonergodic convergence rate of an inexact augmented Lagrangian framework for composite convex programming. Math. Oper. Res. 44(2):632–650.Link, Google Scholar
• Lu Z, Zhou Z (2018) Iteration-complexity of first-order augmented Lagrangian methods for convex conic programming. Preprint, submitted March 27, https://arxiv.org/abs/1803.09941.Google Scholar
• Ma R, Lin Q, Yang T (2019) Proximally constrained methods for weakly convex optimization with weakly convex constraints. Preprint, submitted August 27, https://arxiv.org/abs/1908.01871v2.Google Scholar
• Necoara I, Nedelcu V (2013) Rate analysis of inexact dual first-order methods application to dual decomposition. IEEE Trans. Automatatic Control 59(5):1232–1243.Google Scholar
• Nedelcu V, Necoara I, Tran-Dinh Q (2014) Computational complexity of inexact gradient augmented Lagrangian methods: Application to constrained MPC. SIAM J. Control Optim. 52(5):3109–3134.Google Scholar
• Powell MJ (1969) A method for non-linear constraints in minimization problems. Fletcher R, ed. Optimization (Academic Press, New York), 283–298.Google Scholar
• Rigollet P, Tong X (2011) Neyman-Pearson classification, convexity and stochastic constraints. J. Machine Learn. Res. 12(Oct):2831–2855.Google Scholar
• Rockafellar RT (1970) Convex Analysis (Princeton University Press, Princeton, NJ).Google Scholar
• Rockafellar RT (1973) A dual approach to solving nonlinear programming problems by unconstrained optimization. Math. Programming 5(1):354–373.Google Scholar
• Sahin MF, Alacaoglu A, Latorre F, Cevher V (2019) An inexact augmented Lagrangian framework for nonconvex optimization with nonlinear constraints. Advances in Neural Information Processing Systems (Neural Information Processing Systems Foundation Inc., San Diego), 13943–13955.Google Scholar
• Scott C, Nowak R (2005) A Neyman-Pearson approach to statistical learning. IEEE Trans. Inform. Theory 51(11):3806–3819.Google Scholar
• Xu Y (2017) First-order methods for constrained convex programming based on linearized augmented Lagrangian function. Preprint, submitted November 21, https://arxiv.org/abs/1711.08020.Google Scholar
• Xu Y (2021) Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming. Math. Programming 185:199–244.Google Scholar
• Yang Z, Oja E (2012) Clustering by low-rank doubly stochastic matrix decomposition. Proc. 29th Internat. Conf. Machine Learn. (Omnipress, Madison, WI), 707–714.Google Scholar