Open Problem—Iterative Schemes for Stochastic Optimization: Convergence Statements and Limit Theorems

References

• Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1):183–202.Google Scholar
• Blanchet J, Cartis C, Menickelly M, Scheinberg K (2019) Convergence rate analysis of a stochastic trust region method via supermartingales. INFORMS J. Optim. 1(2):91–183.Google Scholar
• Chang KH, Hong LJ, Wan H (2013) Stochastic trust-region response-surface method (STRONG)—A new response-surface framework for simulation optimization. INFORMS J. Comput. 25(2):230–243.Link, Google Scholar
• Chen H-F (2002) Stochastic Approximation and Its Applications, vol. 64 (Kluwer Academic Publishers, Dordrecht, Netherlands).Google Scholar
• Chen R, Menickelly M, Scheinberg K (2018) Stochastic optimization using a trust-region method and random models. Math. Programming 169(2):447–487.Google Scholar
• Chow YS, Teicher H (2012) Probability Theory: Independence, Interchangeability, Martingales (Springer-Verlag, New York).Google Scholar
• Curtis FE, Robinson DP (2019) Exploiting negative curvature in deterministic and stochastic optimization. Math. Programming 176(1–2):69–94.Google Scholar
• Facchinei F, Pang JS (2007) Finite-Dimensional Variational Inequalities and Complementarity Problems (Springer-Verlag, New York).Google Scholar
• Feller W (1945) The fundamental limit theorems in probability. Bull. Amer. Math. Soc. 51(11):800–832.Google Scholar
• Ghadimi S, Lan G (2016) Accelerated gradient methods for nonconvex nonlinear and stochastic programming. Math. Programming 156(1–2):59–99.Google Scholar
• Ghadimi S, Lan G, Zhang H (2016) Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization. Math. Programming 155(1–2):267–305.Google Scholar
• Iusem AN, Jofré A, Oliveira RI, Thompson P (2019) Variance-based extragradient methods with line search for stochastic variational inequalities. SIAM J. Optim. 29(1):175–206.Google Scholar
• Jalilzadeh A, Shanbhag UV (2016) eg-VSSA: An extragradient variable sample-size stochastic approximation scheme: Error analysis and complexity trade-offs. 2016 Winter Simulation Conf. (WSC) (Institute of Electrical and Electronics Engineers, Piscataway, NJ), 690–701.Google Scholar
• Jalilzadeh A, Nedić A, Shanbhag UV, Yousefian F (2018a) A variable sample-size stochastic quasi-Newton method for smooth and nonsmooth stochastic convex optimization. 2018 IEEE Conf. Decision Control (CDC) (Institute of Electrical and Electronics Engineers, Piscataway, NJ), 4097–4102.Google Scholar
• Jalilzadeh A, Shanbhag UV, Blanchet JH, Glynn PW (2018b) Optimal smoothed variable sample-size accelerated proximal methods for structured nonsmooth stochastic convex programs. Preprint arXiv:1803.00718, submitted March 2, https://arxiv.org/abs/1803.00718.Google Scholar
• Jofré A, Thompson P (2019) On variance reduction for stochastic smooth convex optimization with multiplicative noise. Math. Program. 174(1–2):253–292.Google Scholar
• Juditsky A, Nemirovski A, Tauvel C (2011) Solving variational inequalities with stochastic mirror-prox algorithm. Stochastic Systems 1(1):17–58.Link, Google Scholar
• Koshal J, Nedić A, Shanbhag UV (2013) Regularized iterative stochastic approximation methods for stochastic variational inequality problems. IEEE Trans. Automatic Control 58(3):594–609.Google Scholar
• Kushner H, Yin GG (2003) Stochastic Approximation and Recursive Algorithms and Applications, vol. 35 (Springer-Verlag, New York).Google Scholar
• Lindeberg JW (1922) Eine neue herleitung des exponentialgesetzes in der wahrscheinlichkeitsrechnung. Mathematische Zeitschrift 15(1):211–225.Google Scholar
• Lucchi A, McWilliams B, Hofmann T (2015) A variance reduced stochastic Newton method. Preprint arXiv:1503.08316, submitted March 28, https://arxiv.org/abs/1503.08316.Google Scholar
• Mandt S, Hoffman MD, Blei DM (2017) Stochastic gradient descent as approximate Bayesian inference. J. Machine Learn. Res. 18(1):4873–4907.Google Scholar
• Moguerza JM, Prieto FJ (2003) An augmented Lagrangian interior-point method using directions of negative curvature. Math. Programming 95(3):573–616.Google Scholar
• Mokhtari A, Ribeiro A (2014) RES: Regularized stochastic BFGS algorithm. IEEE Trans. Signal Processing 62(23):6089–6104.Google Scholar
• Nesterov YE (1983) A method for solving the convex programming problem with convergence rate of (1/k2). Soviet Math. Doklady 27(2):372–376.Google Scholar
• Nocedal J, Wright S (2006) Numerical Optimization. (Springer-Verlag, New York).Google Scholar
• Paquette C, Scheinberg K (2018) A stochastic line search method with convergence rate analysis. Preprint, submitted July 20, https://arxiv.org/abs/1807.07994.Google Scholar
• Shanbhag UV, Blanchet JH (2015) Budget-constrained stochastic approximation. Proc. 2015 Winter Simulation Conf. (Institute of Electrical and Electronics Engineers, Piscataway, NJ), 368–379.Google Scholar
• Shashaani S, Hashemi FS, Pasupathy R (2018) ASTRO-DF: A class of adaptive sampling trust-region algorithms for derivative-free stochastic optimization. SIAM J. Optim. 28(4):3145–3176.Google Scholar
• Yousefian F, Nedić A, Shanbhag UV (2013) A regularized smoothing stochastic approximation (RSSA) algorithm for stochastic variational inequality problems. Winter Simulations Conf.: Simulation Making Decisions Complex World, WSC 2013 (Institute of Electrical and Electronics Engineers, Piscataway, NJ), 933–944.Google Scholar
• Yousefian F, Nedić A, Shanbhag UV (2014) Optimal robust smoothing extragradient algorithms for stochastic variational inequality problems. 53rd IEEE Conf. Decision Control (Institute of Electrical and Electronics Engineers, Piscataway, NJ), 5831–5836.Google Scholar
• Yousefian F, Nedić A, Shanbhag UV (2017) On smoothing, regularization, and averaging in stochastic approximation methods for stochastic variational inequality problems. Math. Programming 165(1):391–431.Google Scholar
• Zhou C, Gao W, Goldfarb D (2017) Stochastic adaptive quasi-Newton methods for minimizing expected values. Proc. 34th Internat. Conf. Machine Learn. vol. 70, 4150–4159.Google Scholar