Last-Iterate Convergence in No-Regret Learning: Games with Reference Effects Under Logit Demand

References

• Agrawal S, Tang W (2024) Dynamic pricing and learning with long-term reference effects. Preprint, submitted February 19, https://arxiv.org/abs/2402.12562.Google Scholar
• Arrowsmith DK, Place CM (1990) An Introduction to Dynamical Systems (Cambridge University Press, Cambridge, UK).Google Scholar
• Ba W, Lin T, Zhang J, Zhou Z (2021) Doubly optimal no-regret online learning in strongly monotone games with bandit feedback. Preprint, submitted December 6, https://arxiv.org/abs/2112.02856.Google Scholar
• Boyd S, Xiao L, Mutapcic A (2003) Subgradient methods. Lecture notes of EE392o, Stanford University, Autumn Quarter 2004:2004–2005, Stanford University, Stanford, CA.Google Scholar
• Bravo M, Leslie D, Mertikopoulos P (2018) Bandit learning in concave N-person games. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds. Advances in Neural Information Processing Systems, vol. 31 (Curran Associates Inc., Red Hook, NY), 5666–5676.Google Scholar
• Briesch RA, Krishnamurthi L, Mazumdar T, Raj SP (1997) A comparative analysis of reference price models. J. Consumer Res. 24(2):202–214.Crossref, Google Scholar
• Chen N, Nasiry J (2020) Does loss aversion preclude price variation? Manufacturing Service Oper. Management 22(2):383–395.Link, Google Scholar
• Chen X, Hu P, Hu Z (2017) Efficient algorithms for the dynamic pricing problem with reference price effect. Management Sci. 63(12):4389–4408.Link, Google Scholar
• Colombo L, Labrecciosa P (2021) Dynamic oligopoly pricing with reference-price effects. Eur. J. Oper. Res. 288(3):1006–1016.Crossref, Google Scholar
• den Boer AV, Keskin NB (2022) Dynamic pricing with demand learning and reference effects. Management Sci. 68(10):7112–7130.Link, Google Scholar
• Federgruen A, Lu L (2016) Price competition based on relative prices. Columbia Business School Research Paper No. 13-9, Columbia University, New York.Google Scholar
• Golrezaei N, Jaillet P, Liang JCN (2020) No-regret learning in price competitions under consumer reference effects. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Advances in Neural Information Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 20766–20778.Google Scholar
• Goyal V, Li S, Mehrotra S (2023) Learning to price under competition for multinomial logit demand. Preprint, submitted October 10, http://dx.doi.org/10.2139/ssrn.4572453.Google Scholar
• Guo MA, Shen ZJM (2024) Oligopoly price competitions under exogenous and endogenous reference effects. Preprint, submitted February 11, https://ssrn.com/abstract=4742001.Google Scholar
• Guo MA, Jiang H, Shen ZJM (2022) Multi-product dynamic pricing with reference effects under logit demand. Preprint, submitted August 12, http://dx.doi.org/10.2139/ssrn.4189049.Google Scholar
• Guo MA, Ying D, Lavaei J, Shen ZJ (2023) No-regret learning in dynamic competition with reference effects under logit demand. Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S, eds. Advances in Neural Information Processing Systems, vol. 36 (Curran Associates Inc., Red Hook, NY), 10567–10603.Google Scholar
• Han Y, Weissman T, Zhou Z (2024) Optimal no-regret learning in repeated first-price auctions. Oper. Res. 73(1):209–238.Google Scholar
• Hardie BG, Johnson EJ, Fader PS (1993) Modeling loss aversion and reference dependence effects on brand choice. Marketing Sci. 12(4):378–394.Link, Google Scholar
• Jiang H, Cao J, Shen ZJM (2022) Intertemporal pricing via nonparametric estimation: Integrating reference effects and consumer heterogeneity. Manufacturing Service Oper. Management 26(1):28–46.Link, Google Scholar
• Kahneman D, Tversky A (1979) Prospect theory: An analysis of decision under risk. Econometrica 47(2):263–292.Crossref, Google Scholar
• Kalyanaram G, Winer RS (1995) Empirical generalizations from reference price research. Marketing Sci. 14(3 suppl):G161–G169.Link, Google Scholar
• Khalil H (2002) Nonlinear Systems (Pearson Education, Prentice Hall, Saddle River, NJ).Google Scholar
• Krishnamurthi L, Mazumdar T, Raj S (1992) Asymmetric response to price in consumer brand choice and purchase quantity decisions. J. Consumer Res. 19(3):387–400.Crossref, Google Scholar
• Li J, So AMC, Ma WK (2020) Understanding notions of stationarity in nonsmooth optimization: A guided tour of various constructions of subdifferential for nonsmooth functions. IEEE Signal Processing Magazine 37(5):18–31.Crossref, Google Scholar
• Lin T, Zhou Z, Mertikopoulos P, Jordan MI (2020) Finite-time last-iterate convergence for multi-agent learning in games. Daume H III, Singh A, eds. Internat. Conf. Machine Learn., vol. 119 (PMLR, New York), 6161–6171.Google Scholar
• McFadden D (1974) Conditional logit analysis of qualitative choice behavior. Zarembka P, ed. Frontiers in Economics (Academic Press, New York), 105–142.Google Scholar
• Mertikopoulos P, Zhou Z (2019) Learning in games with continuous action sets and unknown payoff functions. Math. Programming 173(1):465–507.Google Scholar
• Mertikopoulos P, Papadimitriou C, Piliouras G (2018) Cycles in adversarial regularized learning. Czumaj A, ed. SODA ‘18: Sympos. Discrete Algorithms New Orleans Louisiana (SIAM, Philadelphia), 2703–2717.Google Scholar
• Mertikopoulos P, Lecouat B, Zenati H, Foo C-S, Chandrasekhar V, Piliouras G (2019) Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile. ICLR (Ernest N. Morial Convention Center, New Orleans), 1–23.Google Scholar
• Nesterov Y (2014) Introductory Lectures on Convex Optimization: A Basic Course, vol. 87 (Springer Science & Business Media, New York).Google Scholar
• Palaiopanos G, Panageas I, Piliouras G (2017) Multiplicative weights update with constant step-size in congestion games: Convergence, limit cycles and chaos. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds. Advances in Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY), 5874–5884.Google Scholar
• Popescu I, Wu Y (2007) Dynamic pricing strategies with reference effects. Oper. Res. 55(3):413–429.Link, Google Scholar
• Qin H, Simchi-Levi D, Wang L (2022) Data-driven approximation schemes for joint pricing and inventory control models. Management Sci. 68(9):6591–6609.Link, Google Scholar
• Wang R (2018) When prospect theory meets consumer choice models: Assortment and pricing management with reference prices. Manufacturing Service Oper. Management 20(3):583–600.Link, Google Scholar