Asymptotic Consistency for Nonconvex Risk-Averse Stochastic Optimization with Infinite-Dimensional Decision Spaces

References

• [1] Aliprantis CD, Border KC (2006) Infinite Dimensional Analysis: A Hitchhiker’s Guide, 3rd ed. (Springer, Berlin).Google Scholar
• [2] Artzner P, Delbaen F, Eber JM, Heath D (1999) Coherent measures of risk. Math. Finance 9(3):203–228.Crossref, Google Scholar
• [3] Attouch H (1984) Variational Convergence for Functions and Operators, Applicable Mathematics Series (Pitman, Boston).Google Scholar
• [4] Attouch H, Wets RJB (1989) Epigraphical analysis. Ann. Inst. Henri Poincaré Anal. Non Linéaire 6(suppl):73–100.Crossref, Google Scholar
• [5] Aubin JP, Frankowska H (2009) Sat-Valued Analysis (Springer, Boston).Crossref, Google Scholar
• [6] Beiser F, Keith B, Urbainczyk S, Wohlmuth B (2023) Adaptive sampling strategies for risk-averse stochastic optimization with constraints. IMA J. Numerical Anal. 2023:drac083.Crossref, Google Scholar
• [7] Bendsøe MP, Sigmund O (2003) Topology Optimization: Theory, Methods and Applications (Springer, Berlin).Google Scholar
• [8] Ben-Tal A, Teboulle M (2007) An old-new concept of convex risk measures: The optimized certainty equivalent. Math. Finance 17(3):449–476.Crossref, Google Scholar
• [9] Berner J, Grohs P, Jentzen A (2020) Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations. SIAM J. Math. Data Sci. 2(3):631–657.Crossref, Google Scholar
• [10] Billingsley P (2012) Probability and Measure, Wiley Series on Probability and Statistics (John Wiley & Sons, Hoboken, NJ).Google Scholar
• [11] Bogachev VI (2007) Measure Theory (Springer, Berlin).Crossref, Google Scholar
• [12] Bonnans JF, Shapiro A (2000) Perturbation Analysis of Optimization Problems, Springer Series on Operation Research (Springer, New York).Crossref, Google Scholar
• [13] Borwein JM, Lewis AS (1994) Strong rotundity and optimization. SIAM J. Optim. 4(1):146–158.Crossref, Google Scholar
• [14] Borwein JM, Vanderwerff JD (2010) Convex Functions: Constructions, Characterizations and Counterexamples (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• [15] Curi S, Levy KY, Jegelka S, Krause A (2020) Adaptive sampling for stochastic risk-averse learning. Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H, eds. 34th Conf. Neural Inform. Processing Systems (NeurIPS 2020), vol. 33 (Curran Associates, Inc., Red Hook, NY), 1036–1047.Google Scholar
• [16] Davis D, Drusvyatskiy D (2022) Graphical convergence of subgradients in nonconvex optimization and learning. Math. Oper. Res. 47(1):209–231.Link, Google Scholar
• [17] Dentcheva D, Penev S, Ruszczyński A (2017) Statistical estimation of composite risk functionals and risk optimization problems. Ann. Inst. Statist. Math. 69(4):737–760.Crossref, Google Scholar
• [18] Dong MX, Wets RJB (2000) Estimating density functions: A constrained maximum likelihood approach. J. Nonparametric Statist. 12(4):549–595.Crossref, Google Scholar
• [19] Dontchev AL, Zolezzi T (1993) Well-Posed Optimization Problems, Lecture Notes in Mathematics, vol. 1543 (Springer, Berlin).Crossref, Google Scholar
• [20] Dudley RM (2002) Real Analysis and Probability, Cambridge Studies in Advanced Mathematics, vol. 74 (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• [21] Dudley RM, Norvaiša R (2011) Concrete Functional Calculus, Springer Monographs in Mathematics (Springer, New York).Crossref, Google Scholar
• [22] Dupačová J, Wets RJB (1988) Asymptotic behavior of statistical estimators and of optimal solutions of stochastic optimization problems. Ann. Statist. 16(4):1517–1549.Crossref, Google Scholar
• [23] Föllmer H, Schied A (2002) Convex measures of risk and trading constraints. Finance Stochastics 6(4):429–447.Crossref, Google Scholar
• [24] Garreis S, Ulbrich M (2019) A fully adaptive method for the optimal control of semilinear elliptic PDEs under uncertainty using low-rank tensors. Technical report, Technische Universität München, Munich.Google Scholar
• [25] Garreis S, Surowiec TM, Ulbrich M (2021) An interior-point approach for solving risk-averse PDE-constrained optimization problems with coherent risk measures. SIAM J. Optim. 31(1):1–19.Crossref, Google Scholar
• [26] Geiersbach C, Scarinci T (2021) Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces. Comput. Optim. Appl. 78(3):705–740.Crossref, Google Scholar
• [27] Gwinner J, Jadamba B, Khan AA, Raciti F (2022) Uncertainty Quantification in Variational Inequalities: Theory, Numerics, and Applications (CRC Press, Boca Raton, FL).Google Scholar
• [28] Hertlein L, Rauls AT, Ulbrich M, Ulbrich S (2022) An inexact bundle method and subgradient computations for optimal control of deterministic and stochastic obstacle problems. Hintermüller M, Herzog R, Kanzow C, Ulbrich M, Ulbrich S, eds. Non-Smooth and Complementarity-Based Distributed Parameter Systems: Simulation and Hierarchical Optimization, International Series of Numerical Mathematics, vol. 172 (Birkhäuser, Cham, Switzerland), 467–497.Crossref, Google Scholar
• [29] Hille E, Phillips RS (1974) Functional Analysis and Semi-Groups (AMS, Providence, RI).Google Scholar
• [30] Hoffhues M, Römisch W, Surowiec TM (2021) On quantitative stability in infinite-dimensional optimization under uncertainty. Optim. Lett. 15(8):2733–2756.Crossref, Google Scholar
• [31] Huber PJ (1967) The behavior of maximum likelihood estimates under nonstandard conditions. Le Cam LM, Neyman J, eds. Proc. Fifth Berkeley Sympos. Math. Statist. Probab., vol. 1 (University of California Press, Berkeley, CA), 221–233.Google Scholar
• [32] Juditsky A, Kwon J, Moulines E (2023) Unifying mirror descent and dual averaging. Math. Programming 199:793–830.Crossref, Google Scholar
• [33] King AJ, Rockafellar RT (1993) Asymptotic theory for solutions in statistical estimation and stochastic programming. Math. Oper. Res. 18(1):148–162.Link, Google Scholar
• [34] Kleywegt AJ, Shapiro A, Homem-de Mello T (2002) The sample average approximation method for stochastic discrete optimization. SIAM J. Optim. 12(2):479–502.Crossref, Google Scholar
• [35] Korf LA, Wets RJB (2001) Random LSC functions: An ergodic theorem. Math. Oper. Res. 26(2):421–445.Link, Google Scholar
• [36] Kouri DP, Surowiec TM (2016) Risk-averse PDE-constrained optimization using the conditional value-at-risk. SIAM J. Optim. 26(1):365–396.Crossref, Google Scholar
• [37] Kouri DP, Surowiec TM (2018) Existence and optimality conditions for risk-averse PDE-constrained optimization. SIAM/ASA J. Uncertainty Quantification 6(2):787–815.Crossref, Google Scholar
• [38] Kouri DP, Surowiec TM (2020) Epi-regularization of risk measures. Math. Oper. Res. 45(2):774–795.Link, Google Scholar
• [39] Kouri DP, Surowiec TM (2020) Risk-averse optimal control of semilinear elliptic PDEs. ESAIM Control Optimisation Calculus Variations 26:53.Crossref, Google Scholar
• [40] Lachout P, Liebscher E, Vogel S (2005) Strong convergence of estimators as εn-minimisers of optimisation problems. Ann. Inst. Statist. Math. 57(2):291–313.Crossref, Google Scholar
• [41] Lazarov BS, Sigmund O (2011) Filters in topology optimization based on Helmholtz-type differential equations. Internat. J. Numerical Methods Engrg. 86(6):765–781.Crossref, Google Scholar
• [42] Liu J, Cui Y, Pang JS (2022) Solving nonsmooth and nonconvex compound stochastic programs with applications to risk measure minimization. Math. Oper. Res. 47(4):3051–3083.Link, Google Scholar
• [43] Mei S, Bai Y, Montanari A (2018) The landscape of empirical risk for nonconvex losses. Ann. Statist. 46(6A):2747–2774.Crossref, Google Scholar
• [44] Milz J (2022) Reliable error estimates for optimal control of linear elliptic PDEs with random inputs. Preprint, submitted June 18, https://doi.org/10.48550/arXiv.2206.09160.Google Scholar
• [45] Milz J (2023) Consistency of Monte Carlo estimators for risk-neutral PDE-constrained optimization. Appl. Math. Optim. 87(3):57.Crossref, Google Scholar
• [46] Milz J (2023) Sample average approximations of strongly convex stochastic programs in Hilbert spaces. Optim. Lett. 17:471–492.Crossref, Google Scholar
• [47] Mosco U (1969) Convergence of convex sets and of solutions of variational inequalities. Adv. Math. 3(4):510–585.Crossref, Google Scholar
• [48] Nelsen NH, Stuart AM (2021) The random feature model for input-output maps between Banach spaces. SIAM J. Sci. Comput. 43(5):A3212–A3243.Crossref, Google Scholar
• [49] Pflug GC (1995) Asymptotic stochastic programs. Math. Oper. Res. 20(4):769–789.Link, Google Scholar
• [50] Pflug GC (2003) Stochastic optimization and statistical inference. Handbooks Oper. Res. Management Sci. 10:427–482.Crossref, Google Scholar
• [51] Qi Z, Cui Y, Liu Y, Pang JS (2022) Asymptotic properties of stationary solutions of coupled nonconvex nonsmooth empirical risk minimization. Math. Oper. Res. 47(3):2034–2064.Link, Google Scholar
• [52] Rachev ST (1982) Minimal metrics in the random variables space. Grossmann W, Pflug GC, Wertz W, eds. Probab. Statist. Inference Proc. 2nd Pannonian Sympos. Math. Statist. (Springer, Dordrecht, Netherlands), 319–327.Google Scholar
• [53] Rachev ST (1985) On a class of minimal functionals on a space of probability measures. Theory Probab. Appl. 29(1):41–49.Crossref, Google Scholar
• [54] Rachev ST (1985) The Monge–Kantorovich mass transference problem and its stochastic applications. Theory Probab. Appl. 29(4):647–676.Crossref, Google Scholar
• [55] Rachev ST, Römisch W (2002) Quantitative stability in stochastic programming: The method of probability metrics. Math. Oper. Res. 27(4):792–818.Link, Google Scholar
• [56] Robinson SM (1996) Analysis of sample-path optimization. Math. Oper. Res. 21(3):513–528.Link, Google Scholar
• [57] Römisch W, Schultz R (1991) Distribution sensitivity in stochastic programming. Math. Programming 50(2 series A):197–226.Crossref, Google Scholar
• [58] Römisch W, Surowiec TM (2021) Asymptotic properties of Monte Carlo methods in elliptic PDE-constrained optimization under uncertainty. Preprint, submitted June 11, https://arxiv.org/abs/2106.06347.Google Scholar
• [59] Royset JO (2020) Approximations of semicontinuous functions with applications to stochastic optimization and statistical estimation. Math. Programming 184:289–318.Crossref, Google Scholar
• [60] Royset JO, Wets RJB (2020) Variational analysis of constrained M-estimators. Ann. Statist. 48(5):2759–2790.Crossref, Google Scholar
• [61] Ruszczyński A, Shapiro A (2006) Optimization of convex risk functions. Math. Oper. Res. 31(3):433–452.Link, Google Scholar
• [62] Shapiro A (1989) Asymptotic properties of statistical estimators in stochastic programming. Ann. Statist. 17(2):841–858.Crossref, Google Scholar
• [63] Shapiro A (1991) Asymptotic analysis of stochastic programs. Ann. Oper. Res. 30(1):169–186.Crossref, Google Scholar
• [64] Shapiro A (1993) Asymptotic behavior of optimal solutions in stochastic programming. Math. Oper. Res. 18(4):829–845.Link, Google Scholar
• [65] Shapiro A (2000) Statistical inference of stochastic optimization problems. Uryasev SP, ed. Probabilistic Constrained Optimization: Methodology and Applications, Probabilistic Constrained Optimization (Springer, Boston), 282–307.Crossref, Google Scholar
• [66] Shapiro A (2013) Consistency of sample estimates of risk averse stochastic programs. J. Appl. Probab. 50(2):533–541.Crossref, Google Scholar
• [67] Shapiro A (2013) On Kusuoka representation of law invariant risk measures. Math. Oper. Res. 38(1):142–152.Link, Google Scholar
• [68] Shapiro A, Nemirovski A (2005) On complexity of stochastic programming problems. Jeyakumar V, Rubinov A, eds. Continuous Optimization: Current Trends and Modern Applications, Applied Optimization, vol. 99 (Springer, Boston), 111–146.Crossref, Google Scholar
• [69] Shapiro A, Dentcheva D, Ruszczyński A (2021) Lectures on Stochastic Programming: Modeling and Theory, 3rd ed., MOS-SIAM Series on Optimization (SIAM, Philadelphia).Crossref, Google Scholar
• [70] Sigmund O, Maute K (2013) Topology optimization approaches. Structural Multidisciplinary Optim. 48(6):1031–1055.Crossref, Google Scholar
• [71] Surowiec TM (2018) Numerical optimization methods for the optimal control of elliptic variational inequalities. Antil H, Kouri DP, Lacasse MD, Ridzal D, eds. Frontiers in PDE-Constrained Optimization, IMA Volumes in Mathematics and Its Applications, vol. 163 (Springer, New York), 123–170.Crossref, Google Scholar
• [72] Wechsung F, Giuliani A, Landreman M, Cerfon AJ, Stadler G (2022) Single-stage gradient-based stellarator coil design: Stochastic optimization. Nuclear Fusion 62(7):076034.Crossref, Google Scholar
• [73] Zeidler E (1990) Nonlinear Functional Analysis and Its Applications II/B: Nonlinear Monotone Operators (Springer, New York).Google Scholar
• [74] Zervos M (1999) On the epiconvergence of stochastic optimization problems. Math. Oper. Res. 24(2):495–508.Link, Google Scholar