Iterative Backpropagation Method for Efficient Gradient Estimation in Bilevel Network Equilibrium Optimization Problems

References

• Antoniou C, Ben-Akiva M, Koutsopoulos HN (2007) Nonlinear Kalman filtering algorithms for on-line calibration of dynamic traffic assignment models. IEEE Trans. Intell. Transportation Systems 8:661–670. Crossref, Google Scholar
• Antoniou C, Azevedo CL, Lu L, Pereira F, Ben-Akiva M (2015) W-SPSA in practice: Approximation of weight matrices and calibration of traffic simulation models. Transportation Res. Procedia 7:233–253.Google Scholar
• Balakrishna R, Ben-Akiva M, Koutsopoulos HN (2007) Offline calibration of dynamic traffic assignment: Simultaneous demand-and-supply estimation. Transportation Res. Rec. 2003(1):50–58. Crossref, Google Scholar
• Bar-Gera H, Boyce D (2006) Solving a non-convex combined travel forecasting model by the method of successive averages with constant step sizes. Transportation Res., Part B: Methodol. 40:351–367. Crossref, Google Scholar
• Bertsekas DP (1999) Nonlinear Programming, 2nd ed. (Athena Scientific, Belmont, MA).Google Scholar
• Cascetta E, Nguyen S (1988) A unified framework for estimating or updating origin/destination matrices from traffic counts. Transportation Res. Part B. 22:437–455. Crossref, Google Scholar
• Chiappone S, Giuffrè O, Granà A, Mauro R, Sferlazza A (2016) Traffic simulation models calibration using speed-density relationship: An automated procedure based on genetic algorithm. Expert Systems Appl. 44:147–155. Crossref, Google Scholar
• Chong L, Osorio C (2017) A Simulation-Based Optimization Algorithm for Dynamic Large-Scale Urban Transportation Problems. Transportation Sci. 52:637–656. Link, Google Scholar
• Clarke FH (1990) Optimization and Nonsmooth Analysis (Society for Industrial and Applied Mathematics, Philadelphia).Crossref, Google Scholar
• Cook S (2012) CUDA Programming: A Developer’s Guide to Parallel Computing with GPUs (Newnes, Boston).Google Scholar
• Daganzo CF (1995) The cell transmission model. Part II: Network Traffic 298:79–93.Google Scholar
• De Cea J, Fernández E (1993) Transit assignment for congested public transport systems: An equilibrium model. Transportation Sci. 27:133–147.Link, Google Scholar
• Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7):2121–2159.Google Scholar
• Florian M, Chen Y (1995) A coordinate descent method for the bi-level O-D matrix adjustment problem. Internat. Trans. Oper. Res. 2:165–179. Crossref, Google Scholar
• Fu X, Lam WHK, Chen BY, Liu Z (2020) Maximizing space-time accessibility in multi-modal transit networks: an activity-based approach. Transp. A Transp. Sci. 0:1–29. Google Scholar
• Hinton G, Srivastava N, Swersky K (2020) Lecture 6a: Overview of Mini-Batch Gradient Descent. https://www.cs.toronto.edu/∼tijmen/csc321/slides/lecture_slides_lec6.pdf.Google Scholar
• Horni A, Nagel K, Axhausen KW (2016) The Multi-Agent Transport Simulation MATSim. (Ubiquity Press London).Crossref, Google Scholar
• Jiang G, Fosgerau M, Lo HK (2020) Route choice, travel time variability, and rational inattention. Transp. Res., Part B: Methodol. 132:188–207. Crossref, Google Scholar
• Karoonsoontawong A, Waller ST (2010) Integrated network capacity expansion and traffic signal optimization problem: Robust bi-level dynamic formulation. Netw. Spat. Econom. 10:525–550. Crossref, Google Scholar
• Kattan L, Abdulhai B (2006) Noniterative approach to dynamic traffic origin–destination estimation with parallel evolutionary algorithms. Transportation Res. Rec. 1964(1):201–210.Crossref, Google Scholar
• Kattan L, Abdulhai B (2011) Comparative analysis of evolutionary, local search, and hybrid approaches to O/D traffic estimation. J. Transportation Engrg. 137(1):46–56.Crossref, Google Scholar
• Kim H, Baek S, Lim Y (2001) Origin-destination matrices estimated with a genetic algorithm from link traffic counts. Transportation Res. Rec. 1771(1):156–163.Crossref, Google Scholar
• Kingma DP, Ba JL (2017) Adam: A method for stochastic optimization. Preprint, submitted January 30, https://arxiv.org/abs/1412.6980.Google Scholar
• Kuiteing AK, Marcotte P, Savard G (2018) Pricing and revenue maximization over a multicommodity transportation network: the nonlinear demand case. Comput. Optim. Appl. 71:641–671. Crossref, Google Scholar
• Lee E, Patwary AUZ, Huang W, Lo HK (2020) Transit interchange discount optimization using an agent-based simulation model. Procedia Comput. Sci. 170:702–707.Crossref, Google Scholar
• Lee J-B, Ozbay K (2009) New calibration methodology for microscopic traffic simulation using enhanced simultaneous perturbation stochastic approximation approach. Transportation Res. Rec. (2124):233–240.Crossref, Google Scholar
• Li ZC, Lam WHK, Wong SC (2009) The optimal transit fare structure under different market regimes with uncertainty in the network. Netw. Spat. Econom. 9:191–216. Crossref, Google Scholar
• Liu HX, He X, He B (2009) Method of successive weighted averages (MSWA) and self-regulated averaging schemes for solving stochastic user equilibrium problem. Netw. Spat. Econom. 9:485.Crossref, Google Scholar
• Liu Z, Wang S, Zhou B, Cheng Q (2017) Robust optimization of distance-based tolls in a network considering stochastic day to day dynamics. Transportation Res., Part C Emerg. Technol. 79:58–72. Crossref, Google Scholar
• Lo HK, Chen A, Yang H (1999) System time minimization in route guidance with elastic market penetration. Transp. Res. Rec. (1667):25–32.Crossref, Google Scholar
• Lu L, Xu Y, Antoniou C, Ben-Akiva M (2015) An enhanced SPSA algorithm for the calibration of Dynamic Traffic Assignment models. Transportation Res., Part C Emerg. Technol. 51:149–166.Crossref, Google Scholar
• Lu S (2008) Sensitivity of static traffic user equilibria with perturbations in arc cost function and travel demand. Transportation Sci. 42:105–123. Link, Google Scholar
• Noel MM (2012) A new gradient based particle swarm optimization algorithm for accurate computation of global minimum Appl. Soft Comput. 12:353–359. Crossref, Google Scholar
• Oh S, Seshadri R, Azevedo CL, Ben-Akiva ME (2019) Demand calibration of multimodal microscopic traffic simulation using weighted discrete SPSA. Transportation Res. Rec. (2673):503–514.Crossref, Google Scholar
• Osorio C (2019a) Dynamic origin-destination matrix calibration for large-scale network simulators. Transportation Res., Part C Emerg. Technol. 98:186–206. Crossref, Google Scholar
• Osorio C (2019b) High-dimensional offline origin-destination (OD) demand calibration for stochastic traffic simulators of large-scale road networks. Transportation Res., Part B: Methodol. 124:18–43. Crossref, Google Scholar
• Otković II, Tollazzi T, Šraml M, Ištoka Otković I, Tollazzi T, Šraml M (2013) Calibration of microsimulation traffic model using neural network approach. Expert Systems Appl. 40:5965–5974. Crossref, Google Scholar
• Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. 30th Internat. Conf. Machine Learning, ICML 2013 (PMLR, New York).Google Scholar
• Patriksson M (2004) Sensitivity analysis of traffic equilibria. Transportation Sci. 38:258–281. Link, Google Scholar
• Patwary AUZ, Huang W, Lo HK (2021) Metamodel-based calibration of large-scale multimodal microscopic traffic simulation. Transportation Res., Part C Emerg. Technol. 124:102859. Crossref, Google Scholar
• Paz A, Molano V, Martinez E, Gaviria C, Arteaga C (2015) Calibration of traffic flow models using a memetic algorithm. Transportation Res., Part C Emerg. Technol. 55:432–443.Crossref, Google Scholar
• Prakash AA, Seshadri R, Antoniou C, Pereira FC, Ben-Akiva M (2018) Improving scalability of generic online calibration for real-time dynamic traffic assignment systems. Transportation Res. Rec. (2672):79–92.Crossref, Google Scholar
• Raadsen MPH, Bliemer MCJ, Bell MGH (2016) An efficient and exact event-based algorithm for solving simplified first order dynamic network loading problems in continuous time. Transportation Res., Part B: Methodol. 92:191–210. Crossref, Google Scholar
• Sheffi Y (1985) Urban Transportation Networks (Prentice-Hall, Inc., Englewood Cliffs, NJ).Google Scholar
• Spall JC (1992) Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Automat. Control 37(3):332–341.Crossref, Google Scholar
• Spiess H (1990) A gradient approach for the O-D matrix adjustment problem. Cent. Res. Transp. Univ. Montr. Canada. 693:1–11.Google Scholar
• Szeto WY (2003) Dynamic traffic assignment: formulations, properties, and extensions. ProQuest Diss. Theses. The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, https://doi.org/10.14711/thesis-b805492.Google Scholar
• Tobin RL, Friesz TL (1988) Sensitivity analysis for equilibrium network flow. Transportation Sci. 22:242–250. Link, Google Scholar
• Toledo T, Kolechkina T (2013) Estimation of dynamic origin-destination matrices using linear assignment matrix approximations. IEEE Trans. Intell. Transportation Systems 14:618–626. Crossref, Google Scholar
• Tympakianaki A, Koutsopoulos HN, Jenelius E (2018) Robust SPSA algorithms for dynamic OD matrix estimation. Procedia Comput. Sci. 130:57–64. Crossref, Google Scholar
• Vaze V, Antoniou C, Wen Y, Ben-Akiva M (2009) Calibration of dynamic traffic assignment models with point-to-point traffic surveillance. Transportation Res. Rec. (2090):1–9.Crossref, Google Scholar
• Wardrop JG (1952) Some Theoret. Aspects Road Traffic Res. 1(3):325–362.Google Scholar
• Wong KI, Wong SC, Tong CO, Lam WHK, Lo HK, Yang H, Lo HP (2005) Estimation of origin-destination matrices for a multimodal public transit network. J. Adv. Transportation 39:139–168. Crossref, Google Scholar
• Yang H (1995) Heuristic algorithms for the bilevel origin-destination matrix estimation problem. Transportation Res. Part B. 29:231–242. Crossref, Google Scholar
• Yang H, Bell MGH (1997) Traffic restraint, road pricing and network equilibrium. Transportation Res., Part B: Methodol. 31:303–314. Crossref, Google Scholar
• Yang H, Wang JYT (2002) Travel time minimization vs. reserve capacity maximization in the network design problem. Transportation Res. Rec. 1783:17–26. Crossref, Google Scholar
• Yang H, Meng Q, Bell MGH (2001) Simultaneous estimation of the origin-destination matrices and travel-cost coefficient for congested networks in a stochastic user equilibrium. Transportation Sci. 35:107–123.Link, Google Scholar
• Yang H, Sasaki T, Iida Y, Asakura Y (1992) Estimation of origin-destination matrices from link traffic counts on congested networks. Transportation Res., Part B: Methodol. 26:417–434.Crossref, Google Scholar
• Yperman I (2007) The Link Transmission Model for dynamic network loading. Open Access publications from Katholieke Universiteit Leuven.Google Scholar
• Zhang C, Osorio C, Flötteröd G (2017) Efficient calibration techniques for large-scale traffic simulators. Transportation Res., Part B: Methodol. 97:214–239.Crossref, Google Scholar