Solving Nonsmooth and Nonconvex Compound Stochastic Programs with Applications to Risk Measure Minimization

References

• [1] Artstein Z, Hart S (1981) Law of large numbers for random sets and allocation processes. Math. Oper. Res. 6(4):485–492.Link, Google Scholar
• [2] Bayraksan G, Morton DP (2006) Assessing solution quality in stochastic programs. Math. Programming 108(2):495–514.Crossref, Google Scholar
• [3] Ben-Tal A, Teboulle M (1986) Expected utility, penalty functions, and duality in stochastic nonlinear programming. Management Sci. 32(11):1445–1466.Link, Google Scholar
•  [4] 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
•  [5] Chan TCY, Mahmoudzadeh H, Purdie TG (2014) A robust-CVaR optimization approach with application to breast cancer therapy. Eur. J. Oper. Res. 238(3):876–885.Crossref, Google Scholar
•  [6] Chen R, Menickelly M, Scheinberg K (2018) Stochastic optimization using a trust-region method and random models. Math. Programming 169:447–487.Crossref, Google Scholar
•  [7] Clarke FH (1990) Optimization and Nonsmooth Analysis, vol. 5, Classics in Applied Mathematics (Society of Industrial and Applied Mathematics, Philadelphia).Crossref, Google Scholar
•  [8] Cui Y, Pang J-S (2021) Modern Nonconvex Nondifferentiable Optimization (Society for Industrial and Applied Mathematics, Philadelphia).Crossref, Google Scholar
•  [9] Cui Y, Pang J-S, Sen B (2018) Composite difference-max programs for modern statistical estimation problems. SIAM J. Optim. 28(4):3344–3374.Crossref, Google Scholar
• [10] 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
• [11] Dontchev AL, Rockafellar RT (2009) Implicit Functions and Solution Mappings, vol. 208 (Springer, Berlin).Crossref, Google Scholar
• [12] Drusvyatskiy D, Lewis AS (2018) Error bounds, quadratic growth, and linear convergence of proximal methods. Math. Oper. Res. 43(3):919–948.Link, Google Scholar
• [13] El Ghaoui L, Oks M, Oustry F (2003) Worst-case value-at-risk and robust portfolio optimization: A conic programming approach. Oper. Res. 51(4):543–556.Link, Google Scholar
• [14] Ermoliev YM, Norkin VI (2013) Sample average approximation method for compound stochastic optimization problems. SIAM J. Optim. 23(4):2231–2263.Crossref, Google Scholar
• [15] Facchinei F, Pang J-S (2007) Finite-Dimensional Variational Inequalities and Complementarity Problems (Springer Science & Business Media, New York).Google Scholar
• [16] Gao R, Kleywegt AJ (2016) Distributionally robust stochastic optimization with Wasserstein distance. Preprint, submitted July 16, https://arxiv.org/abs/1604.02199v2.Google Scholar
• [17] Ghadimi S, Ruszczyński A, Wang M (2020) A single timescale stochastic approximation method for nested stochastic optimization. SIAM J. Optim. 30(1):960–979.Crossref, Google Scholar
• [18] Higle J, Sen S (1991) Stochastic decomposition: An algorithm for two-stage linear programs with recourse. Math. Oper. Res. 16(3):650–669.Link, Google Scholar
• [19] Higle JL, Sen S (1991) Statistical verification of optimality conditions for stochastic programs with recourse. Ann. Oper. Res. 30:215–239.Google Scholar
• [20] Le Thi HA, Van Ngai H, Tao PD (2019) Stochastic difference-of-convex algorithms for solving nonconvex optimization problems. Preprint, submitted November 11, https://arxiv.org/abs/1911.04334v1.Google Scholar
• [21] Homem-de Mello T (2003) Variable-sample methods for stochastic optimization. ACM Trans. Model. Comput. Simulations 13(2):100–133.Google Scholar
• [22] Hu Y, Chen X, He N (2020) Sample complexity of sample average approximation for conditional stochastic optimization. SIAM J. Optim. 30(3):2103–2133.Crossref, Google Scholar
• [23] Hutson V, Pym J, Cloud M (2005) Applications of Functional Analysis and Operator Theory (Elsevier, Amsterdam).Google Scholar
• [24] Liu J, Sen S (2020) Asymptotic results of stochastic decomposition for two-stage stochastic quadratic programming. SIAM J. Optim. 30(1):823–852.Crossref, Google Scholar
• [25] Lotfi S, Zenios SA (2018) Robust VaR and CVaR optimization under joint ambiguity in distributions, means, and covariances. Eur. J. Oper. Res. 269(2):556–576.Crossref, Google Scholar
• [26] Mafusalov A, Uryasev S (2018) Buffered probability of exceedance: Mathematical properties and optimization. SIAM J. Optim. 28(2):1077–1103.Crossref, Google Scholar
• [27] Mafusalov A, Shapiro A, Uryasev S (2018) Estimation and asymptotics for buffered probability of exceedance. Eur. J. Oper. Res. 270(3):826–836.Crossref, Google Scholar
• [28] Norton M, Uryasev S (2017) Error control and Neyman-Pearson classification with buffered probability and support vectors. Research report.Google Scholar
• [29] Norton M, Uryasev S (2019) Maximization of AUC and buffered AUC in binary classification. Math. Programming 174(1-2):575–612.Crossref, Google Scholar
• [30] Nouiehed M, Pang J-S, Razaviyayn M (2019) On the pervasiveness of difference-convexity in optimization and statistics. Math. Programming 174(1-2):195–222.Crossref, Google Scholar
• [31] Pang J-S (1997) Error bounds in mathematical programming. Math. Programming 79(1):299–332.Crossref, Google Scholar
• [32] Pang J-S, Razaviyayn M, Alvarado A (2017) Computing B-stationary points of nonsmooth DC programs. Math. Oper. Res. 42(1):95–118.Link, Google Scholar
• [33] Pflug GC, Pichler A, Wozabal D (2012) The 1/N investment strategy is optimal under high model ambiguity. J. Banking Finance 36(2):410–417.Crossref, Google Scholar
• [34] Puri ML, Ralescu DA (1983) Strong law of large numbers for banach space valued random sets. Ann. Probab. 11(1):222–224.Crossref, Google Scholar
• [35] Qi Z, Cui Y, Liu Y, Pang J-S (2021) Asymptotic properties of stationary solutions of coupled nonconvex nonsmooth empirical risk minimization. Math. Oper. Res., ePub ahead of print November 10, https://doi.org/10.1287/moor.2021.1198.Link, Google Scholar
• [36] Rahimian H, Mehrotra S (2019) Distributionally robust optimization: A review. Preprint, submitted August 13, https://arxiv.org/abs/1908.05659.Google Scholar
• [37] Robbins H, Siegmund D (1971) A convergence theorem for non negative almost supermartingales and some applications. Rustagi JS, ed. Optimizing Methods in Statistics. (Elsevier, Amsterdam), 233–257.Google Scholar
• [38] Royset J (2020) Stability and error analysis for optimization and generalized equations. SIAM J. Optim. 30(1):752–780.Crossref, Google Scholar
• [39] Royset J, Polak E (2007) Extensions of stochastic optimization results to problems with system failure probability functions. J. Optim. Theory Appl. 133:1–18.Crossref, Google Scholar
• [40] Royset JO (2012) Optimality functions in stochastic programming. Math. Programming 135(1):293–321.Crossref, Google Scholar
• [41] Rockafellar RT, Royset JO (2010) On buffered failure probability in design and optimization of structures. Reliability Engrg. System Safety 95(5):499–510.Crossref, Google Scholar
• [42] Rockafellar RT, Uryasev S (2000) Optimization of conditional value-at-risk. J. Risk 2:21–42.Crossref, Google Scholar
• [43] Rockafellar RT, Uryasev S (2002) Conditional value-at-risk for general loss distributions. J. Banking Finance 26(7):1443–1471.Crossref, Google Scholar
• [44] Rockafellar RT, Wets RJ-B (2009) Variational Analysis, vol. 317 (Springer Science & Business Media, New York).Google Scholar
• [45] Rockafellar RT, Uryasev S, Zabarankin M (2006) Generalized deviations in risk analysis. Finance Stochastics 10(1):51–74.Crossref, Google Scholar
• [46] Shapiro A, Xu H (2007) Uniform laws of large numbers for set-valued mappings and subdifferentials of random functions. J. Math. Anal. Appl. 325(2):1390–1399.Crossref, Google Scholar
• [47] Shapiro A, Dentcheva D, Ruszczyński A (2009) Lectures on Stochastic Programming: Modeling and Theory. (Society of Industrial and Applied Mathematics, Philadelphia).Crossref, Google Scholar
• [48] Wächter A (2002) An interior point algorithm for large-scale nonlinear optimization with applications in process engineering. PhD thesis, Carnegie Mellon University, Pittsburgh.Google Scholar
• [49] Wang M, Fang EX, Liu H (2017) Stochastic compositional gradient descent: Algorithms for minimizing compositions of expected-value functions. Math. Programming 161(1-2):419–449.Crossref, Google Scholar
• [50] Yang S, Wang M, Fang EX (2019) Multilevel stochastic gradient methods for nested composition optimization. SIAM J. Optim. 29(1):616–659.Crossref, Google Scholar