Fast Rates for Contextual Linear Optimization

References

• Audibert JY, Tsybakov AB (2007) Fast learning rates for plug-in classifiers. Ann. Statist. 35(2):608–633.Crossref, Google Scholar
• Bartlett PL, Bousquet O, Mendelson S (2005) Local Rademacher complexities. Ann. Statist. 33(4):1497–1537.Crossref, Google Scholar
• Barvinok A (2013) A bound for the number of vertices of a polytope with applications. Combinatorica 33(1):1–10.Crossref, Google Scholar
• Bastani H, Bayati M (2020) Online decision making with high-dimensional covariates. Oper. Res. 68(1):276–294.Link, Google Scholar
• Bertsimas D, Kallus N (2020) From predictive to prescriptive analytics. Management Sci. 66(3):1025–1044.Link, Google Scholar
• Chen X, Owen Z, Pixton C, Simchi-Levi D (2021) A statistical learning approach to personalization in revenue management. Management Sci., ePub ahead of print January 18, https://doi.org/10.1287/mnsc.2020.3772.Google Scholar
• Devroye L, Lugosi G (1995) Lower bounds in pattern recognition and learning. Pattern Recognition 28(7):1011–1018.Crossref, Google Scholar
• Diao S, Sen S (2020) Distribution-free algorithms for learning enabled predictive stochastic programming. Technical Report, http://www.optimization-online.org/.Google Scholar
• Donti P, Amos B, Kolter JZ (2017) Task-based end-to-end model learning in stochastic optimization. Proc. 31st Internat. Conf. Neural Inform. Processing Systems, 5490–5500.Google Scholar
• Dudley R (1987) Universal Donsker classes and metric entropy. Ann. Probab. 15(4):1306–1326.Crossref, Google Scholar
• El Balghiti O, Elmachtoub AN, Grigas P, Tewari A (2019) Generalization bounds in the predict-then-optimize framework. Proc. 33rd Internat. Conf. Neural Inform. Processing Systems, 14412–14421.Google Scholar
• Elmachtoub AN, Grigas P (2021) Smart “predict, then optimize.” Management Sci. 68(1):9–26.Link, Google Scholar
• Elmachtoub AN, Liang JCN, McNellis R (2020) Decision trees for decision-making under the predict-then-optimize framework. Proc. 37th Internat. Conf. Machine Learn., 2858–2867.Google Scholar
• Estes A, Richard JP (2019) Objective-aligned regression for two-stage linear programs. Preprint, submitted October 23, https://dx.doi.org/10.2139/ssrn.3469897.Google Scholar
• Foster DJ, Rakhlin A, Simchi-Levi D, Xu Y (2020) Instance-dependent complexity of contextual bandits and reinforcement learning. Preprint, submitted October 7, https://arxiv.org/abs/2010.03104.Google Scholar
• Goldenshluger A, Zeevi A (2013) A linear response bandit problem. Stochastic Systems 3(1):230–261.Link, Google Scholar
• Hanneke S (2011) Rates of convergence in active learning. Ann. Statist. 39(1):333–361.Crossref, Google Scholar
• Henk M, Richter-Gebert J, Ziegler GM (2018) Basic properties of convex polytopes. Goodman JE, O’Rourke J, Toth CD, eds. Handbook of Discrete and Computational Geometry (CRC Press, Boca Raton, FL), 255–382.Google Scholar
• Ho CP, Hanasusanto GA (2019) On data-driven prescriptive analytics with side information: A regularized Nadaraya-Watson approach. Technical Report, http://www.optimization-online.org/.Google Scholar
• Ho-Nguyen N, Kilinç-Karzan F (2020) Risk guarantees for end-to-end prediction and optimization processes. Preprint, submitted December 30, https://arxiv.org/abs/2012.15046.Google Scholar
• Hu Y, Kallus N, Mao X (2020) Smooth contextual bandits: Bridging the parametric and non-differentiable regret regimes. PMLR 125:2007–2010.Google Scholar
• Kallus N, Mao X (2020) Stochastic optimization forests. Management Sci., https://pubsonline.informs.org/doi/10.1287/opre.2021.2237.Google Scholar
• Koltchinskii V (2006) Local Rademacher complexities and oracle inequalities in risk minimization. Ann. Statist. 34(6):2593–2656.Google Scholar
• Loke G, Tang Q, Xiao Y (2020) Decision-driven regularization: Harmonizing the predictive and prescriptive. Technical Report, https://www.ssrn.com/.Google Scholar
• Massart P, Nédélec É (2006) Risk bounds for statistical learning. Ann. Statist. 34(5):2326–2366.Crossref, Google Scholar
• McCullagh P, Nelder JA (1989) Generalized Linear Models (Chapman & Hall/CRC, London).Crossref, Google Scholar
• Notz PM, Pibernik R (2021) Prescriptive analytics for flexible capacity management. Management Sci., ePub ahead of print May 6, https://doi.org/10.1287/mnsc.2020.3867.Google Scholar
• Perchet V, Rigollet P (2013) The multi-armed bandit problem with covariates. Ann. Statist. 41(2):693–721.Crossref, Google Scholar
• Rigollet P, Zeevi A (2010) Nonparametric bandits with covariates. Preprint, submitted March 8, https://arxiv.org/abs/1003.1630.Google Scholar
• Shalev-Shwartz S, Ben-David S (2014) Understanding Machine Learning: From Theory to Algorithms (Cambridge University Press, New York).Crossref, Google Scholar
• Tsybakov AB (2004) Optimal aggregation of classifiers in statistical learning. Ann. Statist. 32(1):135–166.Crossref, Google Scholar
• Vahn GY, Rudin C (2019) The big data newsvendor: Practical insights from machine learning. Oper. Res. 67(1):90–108.Link, Google Scholar
• Van Der Vaart A, Wellner JA (2009) A note on bounds for VC dimensions. IMS Collections 5:103–107.Google Scholar
• Vapnik V, Chervonenkis A (1974) Theory of Pattern Recognition (Nauka, Moscow).Google Scholar