Private Optimal Inventory Policy Learning for Feature-Based Newsvendor with Unknown Demand

References

• Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L (2016) Deep learning with differential privacy. Proc. 2016 ACM SIGSAC Conf. Comput. Comm. Security (Association for Computing Machinery, New York), 308–318.Google Scholar
• Avella-Medina M, Bradshaw C, Loh PL (2023) Differentially private inference via noisy optimization. Ann. Statist. 51(5):2067–2092.Crossref, Google Scholar
• Bach F, Jenatton R, Mairal J, Obozinski G (2012) Optimization with sparsity-inducing penalties. Foundations Trends Machine Learning 4(1):1–106.Crossref, Google Scholar
• Balle B, Kairouz P, McMahan B, Thakkar O, Guha Thakurta A (2020) Privacy amplification via random check-ins. Proc. 34th Internat. Conf. Neural Inform. Processing Systems (NIPS ’20) (Curran Associates Inc., Red Hook, NY), 4623–4634.Google Scholar
• Ban GY, Rudin C (2019) The big data newsvendor: Practical insights from machine learning. Oper. Res. 67(1):90–108.Link, Google Scholar
• Bassily R, Smith A, Thakurta A (2014) Private empirical risk minimization: Efficient algorithms and tight error bounds. IEEE 55th Annual Sympos. Foundations Comput. Sci. (IEEE, Piscataway, NJ), 464–473.Google Scholar
• Bassily R, Feldman V, Talwar K, Guha Thakurta A (2019) Private stochastic convex optimization with optimal rates. Proc. 33rd Internat. Conf. Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 11282–11291.Google Scholar
• Beutel AL, Minner S (2012) Safety stock planning under causal demand forecasting. Internat. J. Production Econom. 140(2):637–645.Crossref, Google Scholar
• Burnetas AN, Smith CE (2000) Adaptive ordering and pricing for perishable products. Oper. Res. 48(3):436–443.Link, Google Scholar
• Buttler S, Philippi A, Stein N, Pibernik R (2022) A meta analysis of data-driven newsvendor approaches. ICLR 2022 Workshop Setting Up ML Evaluation Standards Accelerate Progress (ICLR, Appleton, WI).Google Scholar
• Cai TT, Wang Y, Zhang L (2021) The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy. Ann. Statist. 49(5):2825–2850.Crossref, Google Scholar
• Chaudhuri K, Monteleoni C (2008) Privacy-preserving logistic regression. Proc. 21st Internat. Conf. Neural Inform. Processing Systems (NIPS'08) (Curran Associates Inc., Red Hook, NY), 289–296.Google Scholar
• Chaudhuri K, Monteleoni C, Sarwate AD (2011) Differentially private empirical risk minimization. J. Machine Learning Res. 12(3):1069–1109.Google Scholar
• Chen X (2007) Large sample sieve estimation of semi-nonparametric models. Heckman JJ, Leamer EE, eds. Handbook of Econometrics, vol. 6 (Elsevier, Amsterdam), 5549–5632.Google Scholar
• Chen C, Mangasarian OL (1995) Smoothing methods for convex inequalities and linear complementarity problems. Math. Programming 71(1):51–69.Crossref, Google Scholar
• Chen C, Mangasarian OL (1996) A class of smoothing functions for nonlinear and mixed complementarity problems. Comput. Optim. Appl. 5(2):97–138.Crossref, Google Scholar
• Chen X, Liu W, Zhang Y (2019) Quantile regression under memory constraint. Ann. Statist. 47(6):3244–3273.Crossref, Google Scholar
• Chen X, Miao S, Wang Y (2022a) Differential privacy in personalized pricing with nonparametric demand models. Oper. Res. 71(2):581–602.Link, Google Scholar
• Chen X, Simchi-Levi D, Wang Y (2022b) Privacy-preserving dynamic personalized pricing with demand learning. Management Sci. 68(7):4878–4898.Link, Google Scholar
• Dong J, Roth A, Su WJ (2022) Gaussian differential privacy. J. Roy. Statist. Soc. B 84(1):3–37.Crossref, Google Scholar
• Dwork C, McSherry F, Nissim K, Smith A (2006b) Calibrating noise to sensitivity in private data analysis. Halevi S, Rabin T, eds. Theory of Cryptography (Springer, Berlin, Heidelberg), 265–284.Crossref, Google Scholar
• Dwork C, Kenthapadi K, McSherry F, Mironov I, Naor M (2006a) Our data, ourselves: Privacy via distributed noise generation. Vaudenay S, ed. Adv. Cryptology EUROCRYPT 2006, Lecture Notes in Computer Science, vol. 4004 (Springer, Berlin, Heidelberg), 486–503.Google Scholar
• Fainmesser IP, Galeotti A, Momot R (2023) Digital privacy. Management Sci. 69(6):3157–3173.Link, Google Scholar
• Feldman V, Koren T, Talwar K (2020) Private stochastic convex optimization: Optimal rates in linear time. Proc. 52nd Annual ACM SIGACT Sympos. Theory Comput. (Association for Computing Machinery, New York), 439–449.Google Scholar
• Fernandes M, Guerre E, Horta E (2021) Smoothing quantile regressions. J. Bus. Econom. Statist. 39(1):338–357.Crossref, Google Scholar
• Godfrey GA, Powell WB (2001) An adaptive, distribution-free algorithm for the newsvendor problem with censored demands, with applications to inventory and distribution. Management Sci. 47(8):1101–1112.Link, Google Scholar
• Görgülü B, Sarhangian V (2022) A newsvendor approach to design of surgical preference cards. Service Sci. 14(3):213–230.Link, Google Scholar
• Green LV, Savin S, Savva N (2013) “Nursevendor problem”: Personnel staffing in the presence of endogenous absenteeism. Management Sci. 59(10):2237–2256.Link, Google Scholar
• Hannah LA, Powell WB, Blei DM (2010) Nonparametric density estimation for stochastic optimization with an observable state variable. Proc. 23rd Internat. Conf. Neural Inform. Processing Systems - Volume 1 (NIPS’10) (Curran Associates Inc., Red Hook, NY), 820–828.Google Scholar
• He B, Dexter F, Macario A, Zenios S (2012) The timing of staffing decisions in hospital operating rooms: Incorporating workload heterogeneity into the newsvendor problem. Manufacturing Service Oper. Management 14(1):99–114.Link, Google Scholar
• He X, Pan X, Tan KM, Zhou WX (2023) Smoothed quantile regression with large-scale inference. J. Econometrics 232(2):367–388.Crossref, Google Scholar
• Horowitz JL (1998) Bootstrap methods for median regression models. Econometrica 66(6):1327–1351.Crossref, Google Scholar
• Hsu D, Kakade S, Zhang T (2012) A tail inequality for quadratic forms of subgaussian random vectors. Electronic Comm. Probab. 17(52):1–6.Google Scholar
• Hu M, Momot R, Wang J (2022) Privacy management in service systems. Manufacturing Service Oper. Management 24(5):2761–2779.Link, Google Scholar
• Huh WT, Rusmevichientong P (2009) A nonparametric asymptotic analysis of inventory planning with censored demand. Math. Oper. Res. 34(1):103–123.Link, Google Scholar
• Iyengar R, Near JP, Song D, Thakkar O, Thakurta A, Wang L (2019) Toward practical differentially private convex optimization. 2019 IEEE Sympos. Security Privacy (SP) (IEEE, Piscataway, NJ), 299–316.Google Scholar
• Jain P, Thakurta AG (2014) (Near) dimension independent risk bounds for differentially private learning. Xing EP, Jebara T, eds. Proc. 31st Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 32, no. 1 (PMLR, New York), 476–484.Google Scholar
• Koenker R, Bassett G (1978) Regression quantiles. Econometrica 46(1):33–50.Crossref, Google Scholar
• Kunnumkal S, Topaloglu H (2008) Using stochastic approximation methods to compute optimal base-stock levels in inventory control problems. Oper. Res. 56(3):646–664.Link, Google Scholar
• Lee J, Kifer D (2018) Concentrated differentially private gradient descent with adaptive per-iteration privacy budget. Proc. 24th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (Association for Computing Machinery, New York), 1656–1665.Google Scholar
• Lei Y, Miao S, Momot R (2024) Privacy-preserving personalized revenue management. Management Sci. 70(7):4875–4892.Google Scholar
• Levi R, Perakis G, Uichanco J (2015) The data-driven newsvendor problem: New bounds and insights. Oper. Res. 63(6):1294–1306.Link, Google Scholar
• Levi R, Roundy RO, Shmoys DB (2007) Provably near-optimal sampling-based policies for stochastic inventory control models. Math. Oper. Res. 32(4):821–839.Link, Google Scholar
• Liyanage LH, Shanthikumar JG (2005) A practical inventory control policy using operational statistics. Oper. Res. Lett. 33(4):341–348.Crossref, Google Scholar
• Nesterov Y (2005) Smooth minimization of non-smooth functions. Math. Programming 103(1):127–152.Crossref, Google Scholar
• Newey W (1997) Convergence rates and asymptotic normality for series estimators. J. Econometrics 79(1):147–168.Crossref, Google Scholar
• Oroojlooyjadid A, Snyder LV, Takáč M (2020) Applying deep learning to the newsvendor problem. IISE Trans. 52(4):444–463.Crossref, Google Scholar
• Portnoy S, Koenker R (1997) The Gaussian hare and the Laplacian tortoise: Computability of squared-error vs. absolute-error estimators. Statist. Sci. 12(4):279–300.Crossref, Google Scholar
• Powell W, Ruszczyński A, Topaloglu H (2004) Learning algorithms for separable approximations of discrete stochastic optimization problems. Math. Oper. Res. 29(4):814–836.Link, Google Scholar
• See CT, Sim M (2010) Robust approximation to multiperiod inventory management. Oper. Res. 58(3):583–594.Link, Google Scholar
• Slavkovic A, Molinari R (2022) Perturbed M-estimation: A further investigation of robust statistics for differential privacy. Carriquiry AL, Tanur JM, Eddy WF, eds. Statistics in the Public Interest, Springer Series in the Data Sciences (Springer International Publishing, Cham, Switzerland), 337–361.Google Scholar
• Song S, Chaudhuri K, Sarwate AD (2013) Stochastic gradient descent with differentially private updates. 2013 IEEE Global Conf. Signal Inform. Processing (IEEE, Piscataway, NJ), 245–248.Google Scholar
• Tan KM, Wang L, Zhou WX (2022) High-dimensional quantile regression: Convolution smoothing and concave regularization. J. Roy. Statist. Soc. Ser. B. Statist. Methodology 84(1):205–233.Crossref, Google Scholar
• Vershynin R (2018) High-Dimensional Probability: An Introduction with Applications in Data Science, Cambridge Series in Statistical and Probabilistic Mathematics (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Wang YX (2018) Revisiting differentially private linear regression: Optimal and adaptive prediction & estimation in unbounded domain. Preprint, submitted July 7, https://arxiv.org/abs/1803.02596.Google Scholar
• Wang D, Ye M, Xu J (2017) Differentially private empirical risk minimization revisited: Faster and more general. Proc. 31st Internat. Conf. Neural Inform. Processing Systems (NIPS’17) (Curran Associates Inc., Red Hook, NY), 2719–2728.Google Scholar
• Wasserman L, Zhou S (2010) A statistical framework for differential privacy. J. Amer. Statist. Assoc. 105(489):375–389.Crossref, Google Scholar
• Williams EA (2020) Where insights meet privacy: Privacy-preserving machine learning. Forbes (July 2), https://www.forbes.com/sites/forbestechcouncil/2020/07/02/where-insights-meet-privacy-privacy-preserving-machine-learning/?sh=13a873987332.Google Scholar
• Wu X, Li F, Kumar A, Chaudhuri K, Jha S, Naughton J (2017) Bolt-on differential privacy for scalable stochastic gradient descent-based analytics. Proc. 2017 ACM Internat. Conf. Management Data (Association for Computing Machinery, New York), 1307–1322.Google Scholar