Distributionally Constrained Black-Box Stochastic Gradient Estimation and Optimization

References

• Asmussen S, Glynn PW (2007) Stochastic Simulation: Algorithms and Analysis, vol. 57 (Springer Science & Business Media, Boston).Crossref, Google Scholar
• Bai Y, Huang Z, Lam H (2022) Model calibration via distributionally robust optimization: On the NASA Langley Uncertainty Quantification Challenge. Mech. Systems Signal Processing 164:108211.Crossref, Google Scholar
• Barton RR, Schruben LW (2001) Resampling methods for input modeling. Proc. 33nd Conf. Winter Simulation (IEEE Computer Society, Washington, DC), 372–378.Crossref, Google Scholar
• Barton RR, Lam H, Song E (2022) Input uncertainty in stochastic simulation. The Palgrave Handbook of Operations Research (Springer, Berlin), 573–620.Crossref, Google Scholar
• Beck A, Teboulle M (2003) Mirror descent and nonlinear projected subgradient methods for convex optimization. Oper. Res. Lett. 31(3):167–175.Crossref, Google Scholar
• Ben-Tal A, El Ghaoui L, Nemirovski A (2009) Robust Optimization, Princeton Series in Applied Mathematics (Princeton University Press, Princeton, NJ).Google Scholar
• Ben-Tal A, Den Hertog D, De Waegenaere A, Melenberg B, Rennen G (2013) Robust solutions of optimization problems affected by uncertain probabilities. Management Sci. 59(2):341–357.Link, Google Scholar
• Berahas AS, Cao L, Choromanski K, Scheinberg K (2022) A theoretical and empirical comparison of gradient approximations in derivative-free optimization. Foundations Comput. Math. 22(2):507–560.Crossref, Google Scholar
• Bertsimas D, Gupta V, Kallus N (2018) Robust sample average approximation. Math. Programming 171(1–2):217–282.Crossref, Google Scholar
• Chen L, Ma W, Natarajan K, Simchi-Levi D, Yan Z (2022) Distributionally robust linear and discrete optimization with marginals. Oper. Res. 70(3):1822–1834.Google Scholar
• Cheng RC, Holland W (1998) Two-point methods for assessing variability in simulation output. J. Statist. Comput. Simulations 60(3):183–205.Crossref, Google Scholar
• Chick SE (2001) Input distribution selection for simulation experiments: Accounting for input uncertainty. Oper. Res. 49(5):744–758.Link, Google Scholar
• Choromanski K, Rowland M, Sindhwani V, Turner R, Weller A (2018) Structured evolution with compact architectures for scalable policy optimization. Dy J, Krause A, eds. Proc. 35th Internat. Conf. Machine Learn., vol. 80 (PMLR, New York), 970–978.Google Scholar
• Chu C, Blanchet J, Glynn P (2019) Probability functional descent: A unifying perspective on GANs, variational inference, and reinforcement learning. Proc. 36th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 97 (PMLR, New York), 1213–1222.Google Scholar
• Corlu CG, Akcay A, Xie W (2020) Stochastic simulation under input uncertainty: A review. Oper. Res. Perspectives 7:100162.Crossref, Google Scholar
• Cranmer K, Brehmer J, Louppe G (2020) The frontier of simulation-based inference. Proc. Natl. Acad. Sci. USA 117(48):30055–30062.Crossref, Google Scholar
• Csiszár I (1991) Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems. Ann. Statist. 19(4):2032–2066.Crossref, Google Scholar
• Delage E, Ye Y (2010) Distributionally robust optimization under moment uncertainty with application to data-driven problems. Oper. Res. 58(3):595–612.Link, Google Scholar
• Esfahani PM, Kuhn D (2018) Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations. Math. Programming 171(1–2):115–166.Crossref, Google Scholar
• Flaxman AD, Kalai AT, McMahan HB (2005) Online convex optimization in the bandit setting: Gradient descent without a gradient. Proc. 16th Annual ACM-SIAM Sympos. Discrete Algorithms (SIAM, Philadelphia), 385–394.Google Scholar
• Fox BL, Glynn PW (1989) Replication schemes for limiting expectations. Probability Engrg. Inform. Sci. 3(3):299–318.Crossref, Google Scholar
• Fu MC (2006) Gradient estimation. Handbook Oper. Res. Management Sci. 13:575–616.Google Scholar
• Ghadimi S, Lan G (2013) Stochastic first- and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 23(4):2341–2368.Crossref, Google Scholar
• Ghaoui LE, 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
• Ghosh S, Lam H (2015) Mirror descent stochastic approximation for computing worst-case stochastic input models. Proc. Winter Simulation Conf. (IEEE, New York), 425–436.Google Scholar
• Ghosh S, Lam H (2019) Robust analysis in stochastic simulation: Computation and performance guarantees. Oper. Res. 67(1):232–249.Link, Google Scholar
• Glasserman P (2013) Monte Carlo Methods in Financial Engineering, vol. 53 (Springer Science & Business Media, Boston).Google Scholar
• Glasserman P, Xu X (2014) Robust risk measurement and model risk. Quant. Finance 14(1):29–58.Crossref, Google Scholar
• Glynn PW (1990) Likelihood ratio gradient estimation for stochastic systems. Comm. ACM 33(10):75–84.Crossref, Google Scholar
• Goeva A, Lam H, Qian H, Zhang B (2019) Optimization-based calibration of simulation input models. Oper. Res. 67(5):1362–1382.Link, Google Scholar
• Hampel FR, Ronchetti EM, Rousseeuw PJ, Stahel WA (2011) Robust Statistics: The Approach Based on Influence Functions, vol. 196 (John Wiley & Sons, New York).Google Scholar
• Heidergott B, Vázquez-Abad FJ, Pflug G, Farenhorst-Yuan T (2010) Gradient estimation for discrete-event systems by measure-valued differentiation. ACM Trans. Modeling Comput. Simulation 20(1):5/1–5/28.Google Scholar
• Ho YC, Cao X, Cassandras C (1983) Infinitesimal and finite perturbation analysis for queueing networks. Automatica J. IFAC 19(4):439–445.Crossref, Google Scholar
• Hong LJ (2009) Estimating quantile sensitivities. Oper. Res. 57(1):118–130.Link, Google Scholar
• Hu Z, Cao J, Hong LJ (2012) Robust simulation of global warming policies using the DICE model. Management Sci. 58(12):2190–2206.Link, Google Scholar
• Kushner H, Yin GG (2003) Stochastic Approximation and Recursive Algorithms and Applications, vol. 35 (Springer Science & Business Media, Boston).Google Scholar
• Lam H (2018) Sensitivity to serial dependency of input processes: A robust approach. Management Sci. 64(3):1311–1327.Link, Google Scholar
• Lam H, Zhang J (2020) Distributionally constrained stochastic gradient estimation using noisy function evaluations. Proc. 2020 Winter Simulation Conf. (IEEE, New York).Google Scholar
• L’Ecuyer P (1990) A unified view of the IPA, SF, and LR gradient estimation techniques. Management Sci. 36(11):1364–1383.Link, Google Scholar
• Louppe G, Hermans J, Cranmer K (2019) Adversarial variational optimization of non-differentiable simulators. Proc. 22nd Internat. Conf. Artificial Intelligence Statist. (PMLR, New York), 1438–1447.Google Scholar
• Maggiar A, Wachter A, Dolinskaya IS, Staum J (2018) A derivative-free trust-region algorithm for the optimization of functions smoothed via Gaussian convolution using adaptive multiple importance sampling. SIAM J. Optim. 28(2):1478–1507.Crossref, Google Scholar
• Namkoong H, Duchi JC (2016) Stochastic gradient methods for distributionally robust optimization with f-divergences. Proc. 30th Internat. Conf. Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 2216–2224.Google Scholar
• Nemirovski A, Juditsky A, Lan G, Shapiro A (2009) Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4):1574–1609.Crossref, Google Scholar
• Nesterov Y, Spokoiny V (2017) Random gradient-free minimization of convex functions. Foundations Comput. Math. 17(2):527–566.Crossref, Google Scholar
• Peng Y, Fu MC, Hu JQ, Heidergott B (2018) A new unbiased stochastic derivative estimator for discontinuous sample performances with structural parameters. Oper. Res. 66(2):487–499.Link, Google Scholar
• Reddi SJ, Sra S, Póczos B, Smola A (2016) Stochastic Frank-Wolfe methods for nonconvex optimization. Proc. 54th Annual Allerton Conf. Comm. Control Comput. (IEEE, New York), 1244–1251.Google Scholar
• Salimans T, Ho J, Chen X, Sidor S, Sutskever I (2017) Evolution strategies as a scalable alternative to reinforcement learning. Preprint, submitted September 7, https://arxiv.org/abs/1703.03864.Google Scholar
• Sargent RG (2013) Verification and validation of simulation models. J. Simulations 7(1):12–24.Crossref, Google Scholar
• Spall J (1992) Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Automated Control 37(3):332–341.Crossref, Google Scholar
• Tarantola A (2005) Inverse Problem Theory and Methods for Model Parameter Estimation, vol. 89 (Society for Industrial and Applied Mathematics, Philadelphia).Crossref, Google Scholar
• Van Parys BP, Goulart PJ, Kuhn D (2016) Generalized Gauss inequalities via semidefinite programming. Math. Programming 156(1–2):271–302.Crossref, Google Scholar
• Wiesemann W, Kuhn D, Sim M (2014) Distributionally robust convex optimization. Oper. Res. 62(6):1358–1376.Link, Google Scholar
• Zazanis MA, Suri R (1993) Convergence rates of finite-difference sensitivity estimates for stochastic systems. Oper. Res. 41(4):694–703.Link, Google Scholar