Learning to Optimize Contextually Constrained Problems for Real-Time Decision Generation

References

• Agrawal A, Amos B, Barratt S, Boyd S, Diamond S, Kolter JZ (2019) Differentiable convex optimization layers. Adv. Neural Inform. Processing Systems 32:9562–9574.Google Scholar
• Amos B, Kolter JZ (2017) Optnet: Differentiable optimization as a layer in neural networks. Proc. Internat. Conf. Machine Learn., vol. 70 (JMLR.org), 136–145.Google Scholar
• Angalakudati MSB, Calzada J, Chatterjee B, Perakis G, Raad N, Uichanco J (2014) Business analytics for flexible resource allocation under random emergencies. Management Sci. 60(6):1552–1573.Link, Google Scholar
• Angluin D (1988) Queries and concept learning. Machine Learn. 2(4):319–342.Crossref, Google Scholar
• Arjovsky M, Bottou L (2017) Toward principled methods for training generative adversarial networks. Preprint, submitted January 17, https://arxiv.org/abs/1701.04862.Google Scholar
• Babier A, Boutilier JJ, Sharpe MB, McNiven AL, Chan TCY (2018) Inverse optimization of objective function weights for treatment planning using clinical dose-volume histograms. Phys. Medical Biology 63(10):105004.Crossref, Google Scholar
• Babier A, Mahmood R, McNiven AL, Diamant A, Chan TCY (2020) Knowledge-based automated planning with three-dimensional generative adversarial networks. Medical Phys. 47(2):297–306.Crossref, Google Scholar
• Badenbroek R, de Klerk E (2021) Complexity analysis of a sampling-based interior point method for convex optimization. Math. Oper. Res. 47(1):779–811.Google Scholar
• Baeza-Yates R, Liaghat Z (2017) Quality-efficiency trade-offs in machine learning for text processing. Proc. IEEE Internat. Conf. Big Data (IEEE, New York), 897–904.Google Scholar
• Ban GY, Rudin C (2018) The big data newsvendor: Practical insights from machine learning. Oper. Res. 1(67):90–108.Google Scholar
• Ban GY, El Karoui N, Lim AEB (2018) Machine learning and portfolio optimization. Management Sci. 64(3):1136–1154.Link, Google Scholar
• Bansal S, Pachamanova D (2019) Special issue on nonconvex portfolio optimization. Engrg. Econom. 64(3):193–195.Crossref, Google Scholar
• Bartlett PL, Mendelson S (2002) Rademacher and gaussian complexities: Risk bounds and structural results. J. Machine Learn. Res. 3(November):463–482.Google Scholar
• Bastani H, Bastani O, Kim C (2018) Interpreting predictive models for human-in-the-loop analytics. Accessed April 2, 2022, https://api.semanticscholar.org/CorpusID:53073710.Google Scholar
• Bello I, Pham H, Le QV, Norouzi M, Bengio S (2016) Neural combinatorial optimization with reinforcement learning. Preprint, submitted November 29, https://doi.org/10.48550/arXiv.1611.09940.Google Scholar
• Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Machine Learn. 79(1):151–175.Crossref, Google Scholar
• Bendoly E (2011) Linking task conditions to physiology and judgment errors in rm systems. Production Oper. Management 20(6):860–876.Crossref, Google Scholar
• Bendoly E (2013) Real-time feedback and booking behavior in the hospitality industry: Moderating the balance between imperfect judgment and imperfect prescription. J. Oper. Management 31(1–2):62–71.Crossref, Google Scholar
• Bengio Y, Lodi A, Prouvost A (2020) Machine learning for combinatorial optimization: A methodological tour d’horizon. Eur. J. Oper. Res. 290(2):405–421.Google Scholar
• Benson HY, Shanno DF, Vanderbei RJ (2004) Interior-point methods for nonconvex nonlinear programming: Jamming and numerical testing. Math. Programming 99(1):35–48.Crossref, Google Scholar
• Bertsimas D, Cory-Wright R (2022) A scalable algorithm for sparse portfolio selection. INFORMS J. Comput. 34(3):1489–1511.Link, Google Scholar
• Bertsimas D, Kallus N (2019) From predictive to prescriptive analytics. Management Sci. 66(3):1025–1044.Google Scholar
• Bertsimas D, McCord C (2018) Optimization over continuous and multi-dimensional decisions with observational data. Adv. Neural Inform. Processing Systems 21:2966–2974.Google Scholar
• Bertsimas D, Brown DB, Caramanis C (2011) Theory and applications of robust optimization. SIAM Rev. 53(3):464–501.Crossref, Google Scholar
• Bertsimas D, Orfanoudaki A, Weiner RB (2020) Personalized treatment for coronary artery disease patients: A machine learning approach. Health Care Management Sci. 23(4):1–25.Google Scholar
• Besbes O, Gur Y, Zeevi A (2014) Stochastic multi-armed-bandit problem with non-stationary rewards. Adv. Neural Inform. Processing Systems 27:1–9.Google Scholar
• Boutilier JJ, Craig T, Sharpe MB, Chan TCY (2016) Sample size requirements for knowledge-based treatment planning. Medical Phys. 43(3):1212–1221.Crossref, Google Scholar
• Boyd S, Vandenberghe L (2004) Convex Optimization (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Boyd S, Xiao L, Mutapcic A, Mattingley J (2007) Notes on decomposition methods. Notes for EE364B, vol. 635 (Stanford University, Stanford, CA), 1–36.Google Scholar
• Bubeck S, Eldan R (2019) The entropic barrier: Exponential families, log-concave geometry, and self-concordance. Math. Oper. Res. 44(1):264–276.Abstract, Google Scholar
• Campbell AM, Savelsbergh M (2004) Efficient insertion heuristics for vehicle routing and scheduling problems. Transportation Sci. 38(3):369–378.Link, Google Scholar
• Capponi A, Olafsson S, Zariphopoulou T (2021) Personalized robo-advising: Enhancing investment through client interaction. Management Sci. 68(4):2485–2512.Google Scholar
• Castrejon L, Kundu K, Urtasun R, Fidler S (2017) Annotating object instances with a polygon-rnn. Proc. IEEE Conf. Comput. Vision Pattern Recognition (IEEE, Piscataway, NJ), 5230–5238.Google Scholar
• Chan CW, Farias VF, Bambos N, Escobar GJ (2012) Optimizing intensive care unit discharge decisions with patient readmissions. Oper. Res. 60(6):1323–1341.Link, Google Scholar
• Cheung WC, Simchi-Levi D, Zhu R (2022) Hedging the drift: Learning to optimize under nonstationarity. Management Sci. 68(3):1696–1713.Link, Google Scholar
• Conejo AJ, Castillo E, Minguez R, Garcia-Bertrand R (2006) Decomposition Techniques in Mathematical Programming: Engineering and Science Applications (Springer Science & Business Media, New York).Google Scholar
• Cotteleer M, Bendoly E (2015) How behavioral factors affect decisions related to work process deviation. Accessed November 25, 2020, https://www2.deloitte.com/za/en/insights/focus/behavioral-economics/applying-behavioral-principles-in-workplace.html.Google Scholar
• Crankshaw D, Bailis P, Gonzalez JE, Li H, Zhang Z, Franklin MJ, Ghodsi A, et al. (2015) The missing piece in complex analytics: Low latency, scalable model management and serving with velox. Proc. 7th Biennial Conf. Innovative Data Systems Res. (www.cidrdb.org).Google Scholar
• d’Acremont M, Bossaerts P (2008) Neurobiological studies of risk assessment: A comparison of expected utility and mean-variance approaches. Cognition Affective Behav. Neurosci. 8(4):363–374.Crossref, Google Scholar
• Delaney G, Jacob S, Featherstone C, Barton M (2005) The role of radiotherapy in cancer treatment. Cancer 104(6):1129–1137.Crossref, Google Scholar
• Donti P, Amos B, Kolter JZ (2017) Task-based end-to-end model learning in stochastic optimization. Adv. Neural Inform. Processing Systems 30:5484–5494.Google Scholar
• Elmachtoub AN, Grigas P (2021) Smart “predict, then optimize”. Management Sci. 68(1):9–26.Google Scholar
• Emmanouilidis C, Pistofidis P, Bertoncelj L, Katsouros V, Fournaris A, Koulamas C, Ruiz-Carcel C (2019) Enabling the human in the loop: Linked data and knowledge in industrial cyber-physical systems. Annu. Rev. Control 47:249–265.Crossref, Google Scholar
• Faes L, Liu X, Wagner SK, Fu DJ, Balaskas K, Sim DA, Bachmann LM, et al. (2020) A clinician’s guide to artificial intelligence: How to critically appraise machine learning studies. Translation Vision Sci. Tech. 9(2):7–7.Crossref, Google Scholar
• Ferber A, Wilder B, Dilkina B, Tambe M (2020) Mipaal: Mixed integer program as a layer. Proc. AAAI Conf. Artificial Intelligence, vol. 34 (AAAI Press, Palo Alto, CA), 1504–1511.Google Scholar
• Ferreira KJ, Lee BHA, Simchi-Levi D (2015) Analytics for an online retailer: Demand forecasting and price optimization. Manufacturing Services Oper. Management 18(1):69–88.Link, Google Scholar
• Fioretto F, Mak TW, Van Hentenryck P (2020) Predicting AC optimal power flows: Combining deep learning and Lagrangian dual methods. Proc. Conf. AAAI Artificial Intelligence (AAAI Press, Palo Alto, CA), 630–637.Google Scholar
• Foster DJ, Sekhari A, Sridharan K (2018) Uniform convergence of gradients for non-convex learning and optimization. Adv. Neural Inform. Processing Systems 31:8759–8770.Google Scholar
• Geretschläger A, Bojaxhiu B, Dal Pra A, Leiser D, Schmücking M, Arnold A, Ghadjar P, et al. (2015) Definitive intensity modulated radiotherapy in locally advanced hypopharygeal and laryngeal squamous cell carcinoma: Mature treatment results and patterns of locoregional failure. Radiation Oncology 10:20.Crossref, Google Scholar
• Gondzio J (2012) Interior point methods 25 years later. Eur. J. Oper. Res. 218(3):587–601.Crossref, Google Scholar
• Goodfellow I, Bengio Y, Courville A (2016) Deep Learning, vol. 1 (MIT Press, Cambridge, MA).Google Scholar
• Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, et al. (2014) Generative adversarial nets. Adv. Neural Inform. Processing Systems 27:2672–2680.Google Scholar
• Gupta V, Rusmevichientong P (2020) Small-data, large-scale linear optimization with uncertain objectives. Management Sci. 67(1):220–241.Link, Google Scholar
• Gurobi Optimization L (2020) Gurobi optimizer reference manual. http://www.gurobi.com.Google Scholar
• Han J, Luo P, Wang X (2019) Deep self-learning from noisy labels. Proc. IEEE/CVF Internat. Conf. Comput. Vision (IEEE, Piscataway, NJ), 5138–5147.Google Scholar
• Hannah L, Powell W, Blei DM (2010) Nonparametric density estimation for stochastic optimization with an observable state variable. Adv. Neural Inform. Processing Systems 23:820–828.Google Scholar
• Harsanyi JC, Selten R (1988) A General Theory of Equilibrium Selection in Games (MIT Press, Cambridge, MA).Google Scholar
• Hinder O, Ye Y (2018) A one-phase interior point method for nonconvex optimization. Preprint, submitted January 11, https://arxiv.org/abs/1801.03072.Google Scholar
• Hurley WJ, Brimberg J (2015) A note on the sensitivity of the strategic asset allocation problem. Oper. Res. Perspective 2:133–136.Crossref, Google Scholar
• Kaderka R, Hild SJ, Bry VN, Cornell M, Ray XJ, Murphy JD, Atwood TF, et al. (2021) Wide-scale clinical implementation of knowledge-based planning: An investigation of workforce efficiency, need for post-automation refinement, and data-driven model maintenance. Internat. J. Radiation Oncology Biology Physics 111(3):705–715.Crossref, Google Scholar
• Kao YH, Roy BV, Yan X (2009) Directed regression. Adv. Neural Inform. Processing Systems 22:889–897.Google Scholar
• Kearney V, Chan JW, Haaf S, Descovich M, Solberg TD (2018) Dosenet: A volumetric dose prediction algorithm using 3d fully-convolutional neural networks. Phys. Medical Biology 63(23):235022.Crossref, Google Scholar
• Kim Y, Kang D, Jeon M, Lee C (2019) Gan-MP hybrid heuristic algorithm for non-convex portfolio optimization problem. Engrg. Econom. 64(3):196–226.Crossref, Google Scholar
• Konda VR, Tsitsiklis JN (2000) Actor-critic algorithms. Adv. Neural Inform. Processing Systems 12:1008–1014.Google Scholar
• Kool W, van Hoof H, Welling M (2019) Attention, learn to solve routing problems! Proc. Internat. Conf. Learn. Representations (ICLR, Appleton, WI).Google Scholar
• Kotary J, Fioretto F, Van Hentenryck P (2021) Learning hard optimization problems: A data generation perspective. Adv. Neural Inform. Processing Systems 34:24981–24992.Google Scholar
• Lagzi S, Quiroga BF, Romero G, Howard N, Chan TC (2023) Negative externality on service level across priority classes: Evidence from a radiology workflow platform. J. Oper. Management 69(8):1257–1281.Google Scholar
• Lamanna C, Byrne L (2018) Should artificial intelligence augment medical decision making? The case for an autonomy algorithm. AMA J. Ethics 20(9):902–910.Crossref, Google Scholar
• Larsen E, Lachapelle S, Bengio Y, Frejinger E, Lacoste-Julien S, Lodi A (2018) Predicting solution summaries to integer linear programs under imperfect information with machine learning. Preprint, submitted July 31, https://doi.org/10.48550/arXiv.1807.11876.Google Scholar
• Li JYM (2020) Inverse optimization of convex risk functions. Management Sci. 67(11):7113–7141.Google Scholar
• Li C, Chen Y, Shang Y (2021) A review of industrial big data for decision making in intelligent manufacturing. Engrg. Sci. Tech. 29(101021):1–16.Google Scholar
• Li Y, Yang J, Song Y, Cao L, Luo J, Li LJ (2017) Learning from noisy labels with distillation. Proc. IEEE Internat. Conf. Comput. Vision (IEEE, Piscataway, NJ), 1910–1918.Google Scholar
• Liao YH, Kar A, Fidler S (2021) Toward good practices for efficiently annotating large-scale image classification datasets. Proc. IEEE/CVF Conference Computer Vision Pattern Recognition (IEEE, Piscataway, NJ), 4350–4359.Google Scholar
• Low DA, Harms WB, Mutic S, Purdy JA (1998) A technique for the quantitative evaluation of dose distributions. Medical Phys. 25(5):656–661.Crossref, Google Scholar
• Mahmood R, Babier A, McNiven A, Diamant A, Chan TCY (2018) Automated treatment planning in radiation therapy using generative adversarial networks. Doshi-Velez F, Fackler J, Jung K, Kale D, eds. Proc. 3rd Machine Learning Healthcare Conf., vol. 85 (PMLR, New York), 484–499.Google Scholar
• Maurer A (2016) A vector-contraction inequality for rademacher complexities. Proc. Internat. Conf. Algorithmic Learn. Theory (Springer, Berlin), 3–17.Google Scholar
• Mazyavkina N, Sviridov S, Ivanov S, Burnaev E (2021) Reinforcement learning for combinatorial optimization: A survey Computers Oper. Res. 134:105400.Google Scholar
• Melançon GG, Grangier P, Prescott-Gagnon E, Sabourin E, Rousseau LM (2021) A machine learning-based system for predicting service-level failures in supply chains. INFORMS J. Appl. Anal. 51(3):200–212.Link, Google Scholar
• Mišić VV, Perakis G (2020) Data analytics in operations management: A review. Manufacturing Service Oper. Management 22(1):158–169.Link, Google Scholar
• Nair V, Dvijotham K, Dunning I, Vinyals O (2018) Learning fast optimizers for contextual stochastic integer programs. Proc. Thirty-Fourth Conf. Uncertainty Artificial Intelligence, UAI 2018 (Monterrey, CA).Google Scholar
• Natarajan N, Dhillon IS, Ravikumar PK, Tewari A (2013) Learning with noisy labels. Adv. Neural Inform. Processing Systems 26:1196–1204.Google Scholar
• Nesterov Y, Nemirovskii A (1994) Interior-Point Polynomial Algorithms in Convex Programming, vol. 13 (SIAM, Philadelphia).Crossref, Google Scholar
• Neyshabur B, Tomioka R, Srebro N (2015) Norm-based capacity control in neural networks. Proc. Conf. Learn. Theory (PMLR, New York), 1376–1401.Google Scholar
• Nguyen D, Jia X, Sher D, Lin MH, Iqbal Z, Liu H, Jiang S (2019) 3d radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected u-net deep learning architecture. Phys. Medical Biology 64(6):065020.Crossref, Google Scholar
• Pelikan M, Goldberg DE, Lobo FG (2002) A survey of optimization by building and using probabilistic models. Comput. Optim. Appl. 21(1):5–20.Crossref, Google Scholar
• Raghu M, Poole B, Kleinberg J, Ganguli S, Sohl-Dickstein J (2017) On the expressive power of deep neural networks. Proc. Internat. Conf. Machine Learn. (PMLR, New York), 2847–2854.Google Scholar
• Redko I, Morvant E, Habrard A, Sebban M, Bennani Y (2022) A survey on domain adaptation theory. Preprint, submitted July 13, https://arxiv.org/abs/2004.11829.Google Scholar
• Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. Proc. IEEE Conf. Comput. Vision Pattern Recognition (IEEE, Piscataway, NJ), 815–823.Google Scholar
• Settles B (2009) Active learning literature survey. Technical report, University of Wisconsin-Madison, Department of Computer Sciences, Madison, WI.Google Scholar
• Simchi-Levi D, Sun R, Wu MX, Zhu R (2022) Calibrating sales forecast in a pandemic using competitive online non-parametric regression. Preprint, submitted April 11, https://dx.doi.org/10.2139/ssrn.3670264.Google Scholar
• Sun C, Shrivastava A, Singh S, Gupta A (2017) Revisiting unreasonable effectiveness of data in deep learning era. Proc. IEEE Internat. Conf. Comput. Vision (IEEE, Piscataway, NJ), 843–852.Google Scholar
• Swezey RME, Charron B (2018) Large-scale recommendation for portfolio optimization. Proc. 12th ACM Conf. Recommender Systems (ACM, New York), 382–386.Google Scholar
• Vanderbei RJ, Shanno DF (1999) An interior-point algorithm for nonconvex nonlinear programming. Comput. Optim. Appl. 13(1–3):231–252.Crossref, Google Scholar
• Vielma JP, Dunning I, Huchette J, Lubin M (2017) Extended formulations in mixed integer conic quadratic programming. Math. Programming Comput. 9(3):369–418.Crossref, Google Scholar
• Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. Adv. Neural Inform. Processing Systems 28:2692–2700.Google Scholar
• Vollmer S, Mateen BA, Bohner G, Király FJ, Ghani R, Jonsson P, Cumbers S, Jonas A, et al. (2020) Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. bmj 368.Google Scholar
• Wang L, Hu X, Yuan B, Lu J (2015) Active learning via query synthesis and nearest neighbour search. Neurocomputing 147:426–434.Crossref, Google Scholar
• Wang Z, Lin FX, Zhong L, Chishtie M (2012) How far can client-only solutions go for mobile browser speed? Proc. 21st Internat. Conf. World Wide Web (ACM, New York), 31–40.Google Scholar
• Wilder B, Dilkina B, Tambe M (2019) Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization. Proc. Conf. AAAI Artificial Intelligence (AAAI Press, Palo Alto, CA), 1658–1665.Crossref, Google Scholar
• Wu J, Yu Y, Huang C, Yu K (2015) Deep multiple instance learning for image classification and auto-annotation. Proc. IEEE Conf. Comput. Vision Pattern Recognition (IEEE, Piscataway, NJ), 3460–3469.Google Scholar
• Wu B, Kusters M, Kunze-Busch M, Dijkema T, McNutt T, Sanguineti G, Bzdusek K, et al. (2017) Cross-institutional knowledge-based planning (KBP) implementation and its performance comparison with auto-planning engine (APE). J. Eur. Society Therapeutic Radiology Oncology 123(1):57–62.Crossref, Google Scholar
• Yu S, Wang H, Dong C (2023) Learning risk preferences from investment portfolios using inverse optimization. Res. Internat. Bus. Finance 64:101879.Google Scholar
• Zhang Y, Chen W, Ling H, Gao J, Zhang Y, Torralba A, Fidler S (2021a) Image gans meet differentiable rendering for inverse graphics and interpretable 3d neural rendering. Proc. Internat. Conf. Learn. Representations (OpenReview.net).Google Scholar
• Zhang Y, Ling H, Gao J, Yin K, Lafleche JF, Barriuso A, Torralba A, et al. (2021b) Datasetgan: Efficient labeled data factory with minimal human effort. Proc. IEEE Conf. Comput. Vision Pattern Recognition (IEEE, Piscataway, NJ).Google Scholar
• Zhao Y, Laser MS, Lyu Y, Medvidovic N (2018) Leveraging program analysis to reduce user-perceived latency in mobile applications. Proc. 40th Internat. Conf. Software Engrg. (ACM, New York), 176–186.Google Scholar