Lipschitz Stability of Least-Squares Problems Regularized by Functions with ${\mathcal{C}}^2$-Cone Reducible Conjugates

References

• [1] Berk A, Brugiapaglia S, Hoheisel T (2023) Lasso reloaded: A variational analysis perspective with applications to compressed sensing. SIAM J. Math. Data Sci. 5(4):1102–1129.Crossref, Google Scholar
• [2] Berk A, Brugiapaglia S, Hoheisel T (2024) Square root lasso: Well-posedness, Lipschitz stability, and the tuning trade-off. SIAM J. Optim. 34(3):2609–2637.Crossref, Google Scholar
• [3] Bolte J, Pauwels E (2021) Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning. Math. Programming 188(1):19–51.Crossref, Google Scholar
• [4] Bolte J, Pauwels E, Silveti-Falls A (2024) Differentiating nonsmooth solutions to parametric monotone inclusion problems. SIAM J. Optim. 34(1):71–97.Crossref, Google Scholar
• [5] Bolte J, Le T, Pauwels E, Silveti-Falls A (2021) Nonsmooth implicit differentiation for machine-learning and optimization. Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, eds. Advances in Neural Information Processing Systems, vol. 34 (Curran Associates, Red Hook, NY), 13537–13549.Google Scholar
• [6] Bonnans JF, Ramírez C H (2005) Perturbation analysis of second-order cone programming problems. Math. Programming 104(2):205–227.Crossref, Google Scholar
• [7] Bonnans JF, Shapiro A (2000) Perturbation Analysis of Optimization Problems (Springer Science & Business Media, Berlin).Crossref, Google Scholar
• [8] Cui Y, Ding C, Zhao X (2017) Quadratic growth conditions for convex matrix optimization problems associated with spectral functions. SIAM J. Optim. 27(4):2332–2355.Crossref, Google Scholar
• [9] Dontchev AL, Rockafellar RT (1996) Characterizations of strong regularity for variational inequalities over polyhedral convex sets. SIAM J. Optim. 6(4):1087–1105.Crossref, Google Scholar
• [10] Dontchev AL, Rockafellar RT (2014) Implicit Functions and Solution Mappings: A View from Variational Analysis (Springer, New York).Crossref, Google Scholar
• [11] Everink JM, Dong Y, Andersen MS (2024) The geometry and well-posedness of sparse regularized linear regression. Preprint, submitted September 5, https://arxiv.org/abs/2409.03461.Google Scholar
• [12] Fadili J, Nghia TTA, Phan DN (2025) Solution uniqueness of convex optimization problems via the radial cone. J. Optim. Theory Appl. 206(2):40:1–32.Crossref, Google Scholar
• [13] Gfrerer H, Outrata JV (2022) On (local) analysis of multifunctions via subspaces contained in graphs of generalized derivatives. J. Math. Anal. Appl. 508(2):1–37.Crossref, Google Scholar
• [14] Hu C, Yao W, Zhang J (2024) Decomposition method for Lipschitz stability of general LASSO-type problems. Preprint, submitted July 26, https://arxiv.org/abs/2407.18884.Google Scholar
• [15] Klatte D, Kummer B (2002) Nonsmooth Equations in Optimization: Regularity, Calculus, Methods and Applications (Springer, New York).Google Scholar
• [16] Kojima M (1980) Strongly stable stationary solutions in nonlinear programs. Robinson SM, ed. Analysis and Computation of Fixed Points (Academic Press, New York), 93–138.Crossref, Google Scholar
• [17] Kojima M, Hirabayashi R (2009) Continuous deformation of nonlinear programs. Flacco AV, ed. Sensitivity, Stability and Parametric Analysis (Springer, Berlin), 150–198.Google Scholar
• [18] Levy AB, Poliquin RA, Rockafellar RT (2000) Stability of locally optimal solutions. SIAM J. Optim. 10(2):580–604.Crossref, Google Scholar
• [19] Mairal J, Yu B (2012) Complexity analysis of the lasso regularization path. Proc. 29th Internat. Conf. Machine Learn. (Omnipress, Madison, WI), 1835–1842.Google Scholar
• [20] Meng K, Wu P, Yang X (2024) Lipschitz continuity of solution multifunctions of extended ℓ1 regularization problems. Preprint, submitted June 23, https://arxiv.org/abs/2406.16053v1.Google Scholar
• [21] Mordukhovich BS (2006) Variational Analysis and Generalized Differentiation (Springer, Berlin).Crossref, Google Scholar
• [22] Mordukhovich BS, Nghia TT, Rockafellar RT (2015) Full stability in finite-dimensional optimization. Math. Oper. Res. 40(1):226–252.Link, Google Scholar
• [23] Nghia TT (2025) Geometric characterizations of Lipschitz stability for convex optimization problems. SIAM J. Optim. 35(2):927–958.Crossref, Google Scholar
• [24] Poliquin R, Rockafellar RT (1998) Tilt stability of a local minimum. SIAM J. Optim. 8(2):287–299.Crossref, Google Scholar
• [25] Robinson SM (1980) Strongly regular generalized equations. Math. Oper. Res. 5(1):43–62.Link, Google Scholar
• [26] Robinson SM (1984) Local structure of feasible sets in nonlinear programming, part II. Nondegeneracy. Korte B, Ritter K, eds. Mathematical Programming at Oberwolfach II, Mathematical Programming Studies, vol. 22 (Springer, Berlin), 217–230.Crossref, Google Scholar
• [27] Robinson SM (1987) Local structure of feasible sets in nonlinear programming, part III. Stability and sensitivity. Cornet B, Nguyen VH, Vial JP, eds. Nonlinear Analysis and Optimization, Mathematical Programming Studies, vol. 30 (Springer, Berlin), 45–66.Crossref, Google Scholar
• [28] Rockafellar RT (1970) Convex Analysis, Princeton Mathematical Series (Princeton University Press, Princeton, NJ).Crossref, Google Scholar
• [29] Rockafellar RT, Wets RJ (1998) Variational Analysis (Springer, Berlin).Crossref, Google Scholar
• [30] Shapiro A (2003) Sensitivity analysis of generalized equations. J. Math. Sci. 115(4):2554–2565.Crossref, Google Scholar
• [31] Sun D (2006) The strong second-order sufficient condition and constraint nondegeneracy in nonlinear semidefinite programming and their implications. Math. Oper. Res. 31(4):761–776.Link, Google Scholar
• [32] Tibshirani RJ (2013) The lasso problem and uniqueness. Electronic J. Statist. 7:1456–1490.Crossref, Google Scholar
• [33] Vaiter S, Deledalle C, Fadili J, Peyré G, Dossal C (2017) The degrees of freedom of partly smooth regularizers. Ann. Inst. Statist. Math. 69(4):791–832.Crossref, Google Scholar