2000 character limit reached
Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality
Published 9 Jul 2022 in math.OC, cs.LG, and stat.ML | (2207.04173v3)
Abstract: We analyze a stochastic approximation algorithm for decision-dependent problems, wherein the data distribution used by the algorithm evolves along the iterate sequence. The primary examples of such problems appear in performative prediction and its multiplayer extensions. We show that under mild assumptions, the deviation between the average iterate of the algorithm and the solution is asymptotically normal, with a covariance that clearly decouples the effects of the gradient noise and the distributional shift. Moreover, building on the work of H\'ajek and Le Cam, we show that the asymptotic performance of the algorithm with averaging is locally minimax optimal.
- Shabbir Ahmed. Strategic Planning Under Uncertainty: Stochastic Integer Programming Approaches. University of Illinois at Urbana-Champaign, 2000.
- Gradient Flows: In Metric Spaces and in the Space of Probability Measures. Lectures in Mathematics. ETH Zürich. Birkhäuser Basel, 2nd edition, 2008.
- Richard F. Bass. Stochastic Processes. Cambridge University Press, 2011.
- Causal feature discovery through strategic modification. arXiv:2002.07024, 2020.
- Performative prediction in a stateful world. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 6045–6061. PMLR, 2022.
- Stochastic Optimization under Distributional Drift. Journal of Machine Learning Research, 24(147):1–56, 2023.
- Subgradient methods near active manifolds: saddle point avoidance, local convergence, and asymptotic normality. arXiv:2108.11832, 2021.
- Amir Dembo. Probability Theory: STAT310/MATH230. Stanford University, 2021.
- Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, pages 55–70, 2018.
- Implicit Functions and Solution Mappings: A View from Variational Analysis. Springer, 2009.
- Stochastic optimization with decision-dependent distributions. Mathematics of Operations Research, August 2022.
- Asymptotic optimality in stochastic optimization. The Annals of Statistics, 49(1):21–48, 2021.
- Marie Duflo. Random Iterative Models. Stochastic Modeling and Applied Probability. Springer Berlin, Heidelberg, 1997.
- Jitka Dupačová. Optimization under exogenous and endogenous uncertainty. University of West Bohemia in Pilsen, 2006.
- Rick Durrett. Probability: Theory and Examples. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, 5th edition, 2019.
- Vaclav Fabian. On Asymptotic Normality in Stochastic Approximation. The Annals of Mathematical Statistics, 39(4):1327–1332, 1968.
- Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, pages 111–122. ACM, 2016.
- Decision-dependent probabilities in stochastic programs with recourse. Computational Management Science, 15(3):369–395, 2018.
- How to learn when data reacts to your model: performative gradient descent. In International Conference on Machine Learning, pages 4641–4650. PMLR, 2021.
- Regret minimization with performative feedback. In International Conference on Machine Learning, pages 9760–9785. PMLR, 2022.
- A class of stochastic programs with decision dependent random elements. Annals of Operations Research, 82:83–106, 1998.
- Alexander S. Kechris. Classical Descriptive Set Theory. Springer, 1995.
- An Introduction to Variational Inequalities and Their Applications. SIAM, 2000.
- Achim Klenke. Probability Theory: A Comprehensive Course. Springer, 3rd edition, 2020.
- Asymptotics in Statistics: Some Basic Concepts. Springer, 2000.
- Stochastic optimization for performative prediction. In Advances in Neural Information Processing Systems, volume 33, pages 4929–4939. Curran Associates, Inc., 2020.
- Strategic classification is causal modeling in disguise. In International Conference on Machine Learning, pages 6917–6926. PMLR, 2020.
- Outside the echo chamber: Optimizing the performative risk. In International Conference on Machine Learning, pages 7710–7720. PMLR, 2021.
- Multiplayer performative prediction: Learning in decision-dependent games. Journal of Machine Learning Research, 24(202):1–56, 2023.
- Performative prediction. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 7599–7609. PMLR, 2020.
- Multi-agent performative prediction: From global stability and optimality to chaos. arXiv:2201.10483, 2022.
- Acceleration of stochastic approximation by averaging. SIAM Journal on Control and Optimization, 30(4):838–855, 1992.
- Decision-dependent risk minimization in geometrically decaying dynamic environments. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 8081–8088, 2022.
- H. Robbins and D. Siegmund. A convergence theorem for non negative almost supermartingales and some applications. In Optimizing Methods in Statistics, pages 233–257. Academic Press, 1971.
- R. Tyrrell Rockafellar and Roger J.-B. Wets. Variational Analysis. Springer, 1998.
- R. Y. Rubinstein and A. Shapiro. Discrete Event Systems: Sensitivity Analysis and Stochastic Optimization by the Score Function Method. Wiley Series in Probability and Mathematical Statistics. Wiley, 1993.
- Aad W. van der Vaart. Asymptotic Statistics. Cambridge University Press, 1998.
- Aad W. van der Vaart and Jon A. Wellner. Weak Convergence and Empirical Processes. Springer, 1996.
- Pravin Varaiya and Roger J.-B. Wets. Stochastic dynamic optimization approaches and computation. IIASA WP-88-87, Laxenburg, Austria, 1988.
- Martin J. Wainwright. High-Dimensional Statistics: A Non-Asymptotic Viewpoint, volume 48. Cambridge University Press, 2019.
- Stochastic saddle point problems with decision-dependent distributions. SIAM Journal on Optimization, 33(3):1943–1967, 2023.
- Online projected gradient descent for stochastic optimization with decision-dependent distributions. IEEE Control Systems Letters, 6:1646–1651, 2021.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.