Papers
Topics
Authors
Recent
Search
2000 character limit reached

Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributions

Published 23 Feb 2024 in cs.LG and math.OC | (2402.15188v1)

Abstract: This paper studies performative risk minimization, a formulation of stochastic optimization under decision-dependent distributions. We consider the general case where the performative risk can be non-convex, for which we develop efficient parameter-free optimistic optimization-based methods. Our algorithms significantly improve upon the existing Lipschitz bandit-based method in many aspects. In particular, our framework does not require knowledge about the sensitivity parameter of the distribution map and the Lipshitz constant of the loss function. This makes our framework practically favorable, together with the efficient optimistic optimization-based tree-search mechanism. We provide experimental results that demonstrate the numerical superiority of our algorithms over the existing method and other black-box optimistic optimization methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. Online stochastic optimization under correlated bandit feedback. In E. P. Xing and T. Jebara, editors, Proceedings of the 31st International Conference on Machine Learning, volume 32 of Proceedings of Machine Learning Research, pages 1557–1565, Bejing, China, 22–24 Jun 2014. PMLR. URL https://proceedings.mlr.press/v32/azar14.html.
  2. A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption. In A. Garivier and S. Kale, editors, Proceedings of the 30th International Conference on Algorithmic Learning Theory, volume 98 of Proceedings of Machine Learning Research, pages 184–206. PMLR, 22–24 Mar 2019. URL https://proceedings.mlr.press/v98/bartlett19a.html.
  3. Gaming helps! learning from strategic interactions in natural dynamics. In A. Banerjee and K. Fukumizu, editors, Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, volume 130 of Proceedings of Machine Learning Research, pages 1234–1242. PMLR, 13–15 Apr 2021. URL https://proceedings.mlr.press/v130/bechavod21a.html.
  4. Performative prediction in a stateful world. In G. Camps-Valls, F. J. R. Ruiz, and I. Valera, editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 6045–6061. PMLR, 28–30 Mar 2022. URL https://proceedings.mlr.press/v151/brown22a.html.
  5. Static prediction games for adversarial learning problems. Journal of Machine Learning Research, 13(85):2617–2654, 2012. URL http://jmlr.org/papers/v13/brueckner12a.html.
  6. ¡i¿x¡/i¿-armed bandits. Journal of Machine Learning Research, 12(46):1655–1695, 2011a. URL http://jmlr.org/papers/v12/bubeck11a.html.
  7. Lipschitz bandits without the lipschitz constant. In J. Kivinen, C. Szepesvári, E. Ukkonen, and T. Zeugmann, editors, Algorithmic Learning Theory, pages 144–158, Berlin, Heidelberg, 2011b. Springer Berlin Heidelberg. ISBN 978-3-642-24412-4.
  8. Learning strategy-aware linear classifiers. In H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 15265–15276. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/ae87a54e183c075c494c4d397d126a66-Paper.pdf.
  9. Adversarial classification. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’04, page 99–108, New York, NY, USA, 2004. Association for Computing Machinery. ISBN 1581138881. doi: 10.1145/1014052.1014066. URL https://doi.org/10.1145/1014052.1014066.
  10. Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, EC ’18, page 55–70, New York, NY, USA, 2018. Association for Computing Machinery. ISBN 9781450358293. doi: 10.1145/3219166.3219193. URL https://doi.org/10.1145/3219166.3219193.
  11. Approximate regions of attraction in learning with decision-dependent distributions. In F. Ruiz, J. Dy, and J.-W. van de Meent, editors, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, volume 206 of Proceedings of Machine Learning Research, pages 11172–11184. PMLR, 25–27 Apr 2023. URL https://proceedings.mlr.press/v206/dong23b.html.
  12. D. Drusvyatskiy and L. Xiao. Stochastic optimization with decision-dependent distributions. Mathematics of Operations Research, 48(2):954–998, 2023. doi: 10.1287/moor.2022.1287. URL https://doi.org/10.1287/moor.2022.1287.
  13. Black-box optimization of noisy functions with unknown smoothness. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper_files/paper/2015/file/ab817c9349cf9c4f6877e1894a1faa00-Paper.pdf.
  14. M. Hardt and C. Mendler-Dünner. Performative prediction: Past and future, 2023.
  15. Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, ITCS ’16, page 111–122, New York, NY, USA, 2016. Association for Computing Machinery. ISBN 9781450340571. doi: 10.1145/2840728.2840730. URL https://doi.org/10.1145/2840728.2840730.
  16. A. Hoorfar and M. Hassani. Inequalities on the lambert function and hyperpower function. Journal of Inequalities in Pure & Applied Mathematics, 9(2):5–9, 2008. URL http://eudml.org/doc/130024.
  17. How to learn when data reacts to your model: Performative gradient descent. In M. Meila and T. Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 4641–4650. PMLR, 18–24 Jul 2021. URL https://proceedings.mlr.press/v139/izzo21a.html.
  18. How to learn when data gradually reacts to your model. In G. Camps-Valls, F. J. R. Ruiz, and I. Valera, editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 3998–4035. PMLR, 28–30 Mar 2022. URL https://proceedings.mlr.press/v151/izzo22a.html.
  19. Regret minimization with performative feedback. In K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu, and S. Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 9760–9785. PMLR, 17–23 Jul 2022. URL https://proceedings.mlr.press/v162/jagadeesan22a.html.
  20. Lipschitzian optimization without the lipschitz constant. Journal of Optimization Theory and Applications, 79(1):157–181, 1993. doi: 10.1007/BF00941892. URL https://doi.org/10.1007/BF00941892.
  21. L. Kantorovich and G. S. Rubinstein. On a space of totally additive functions. Vestnik Leningrad. Univ, 13:52–59, 1958.
  22. Multi-armed bandits in metric spaces. In Proceedings of the Fortieth Annual ACM Symposium on Theory of Computing, STOC ’08, page 681–690, New York, NY, USA, 2008. Association for Computing Machinery. ISBN 9781605580470. doi: 10.1145/1374376.1374475. URL https://doi.org/10.1145/1374376.1374475.
  23. Q. Li and H.-T. Wai. State dependent performative prediction with stochastic approximation. In G. Camps-Valls, F. J. R. Ruiz, and I. Valera, editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 3164–3186. PMLR, 28–30 Mar 2022. URL https://proceedings.mlr.press/v151/li22c.html.
  24. Pyxab – a python library for 𝒳𝒳\mathcal{X}caligraphic_X-armed bandit and online blackbox optimization algorithms, 2023a. URL https://arxiv.org/abs/2303.04030.
  25. Optimum-statistical collaboration towards general and efficient black-box optimization. Transactions on Machine Learning Research, 2023b. ISSN 2835-8856. URL https://openreview.net/forum?id=ClIcmwdlxn.
  26. Zeroth-order methods for convex-concave min-max problems: Applications to decision-dependent risk minimization. In G. Camps-Valls, F. J. R. Ruiz, and I. Valera, editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 6702–6734. PMLR, 28–30 Mar 2022. URL https://proceedings.mlr.press/v151/maheshwari22a.html.
  27. C. Malherbe and N. Vayatis. Global optimization of Lipschitz functions. In D. Precup and Y. W. Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 2314–2323. PMLR, 06–11 Aug 2017. URL https://proceedings.mlr.press/v70/malherbe17a.html.
  28. Stochastic optimization for performative prediction. In H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 4929–4939. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/33e75ff09dd601bbe69f351039152189-Paper.pdf.
  29. Outside the echo chamber: Optimizing the performative risk. In M. Meila and T. Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 7710–7720. PMLR, 18–24 Jul 2021. URL https://proceedings.mlr.press/v139/miller21a.html.
  30. The social cost of strategic classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* ’19, page 230–239, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450361255. doi: 10.1145/3287560.3287576. URL https://doi.org/10.1145/3287560.3287576.
  31. Performative prediction with neural networks. In F. Ruiz, J. Dy, and J.-W. van de Meent, editors, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, volume 206 of Proceedings of Machine Learning Research, pages 11079–11093. PMLR, 25–27 Apr 2023. URL https://proceedings.mlr.press/v206/mofakhami23a.html.
  32. R. Munos. Optimistic optimization of a deterministic function without the knowledge of its smoothness. In J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K. Weinberger, editors, Advances in Neural Information Processing Systems, volume 24. Curran Associates, Inc., 2011. URL https://proceedings.neurips.cc/paper_files/paper/2011/file/7e889fb76e0e07c11733550f2a6c7a5a-Paper.pdf.
  33. Performative prediction. In H. D. III and A. Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 7599–7609. PMLR, 13–18 Jul 2020. URL https://proceedings.mlr.press/v119/perdomo20a.html.
  34. Decision-dependent risk minimization in geometrically decaying dynamic environments. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pages 8081–8088. AAAI Press, 2022. doi: 10.1609/AAAI.V36I7.20780. URL https://doi.org/10.1609/aaai.v36i7.20780.
  35. M. Shaked and J. Shanthikumar. Stochastic Orders. Springer Series in Statistics. Springer New York, 2007. ISBN 9780387346755.
  36. General parallel optimization a without metric. In A. Garivier and S. Kale, editors, Proceedings of the 30th International Conference on Algorithmic Learning Theory, volume 98 of Proceedings of Machine Learning Research, pages 762–788. PMLR, 22–24 Mar 2019. URL https://proceedings.mlr.press/v98/xuedong19a.html.
  37. A. Slivkins. Multi-armed bandits on implicit metric spaces. In J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K. Weinberger, editors, Advances in Neural Information Processing Systems, volume 24. Curran Associates, Inc., 2011. URL https://proceedings.neurips.cc/paper_files/paper/2011/file/7634ea65a4e6d9041cfd3f7de18e334a-Paper.pdf.
  38. Stochastic simultaneous optimistic optimization. In S. Dasgupta and D. McAllester, editors, Proceedings of the 30th International Conference on Machine Learning, volume 28 of Proceedings of Machine Learning Research, pages 19–27, Atlanta, Georgia, USA, 17–19 Jun 2013. PMLR. URL https://proceedings.mlr.press/v28/valko13.html.
  39. C. Villani. Optimal Transport: Old and New. Grundlehren der mathematischen Wissenschaften. Springer Berlin Heidelberg, 2008. ISBN 9783540710509. URL https://books.google.co.kr/books?id=hV8o5R7_5tkC.
  40. Who leads and who follows in strategic classification? In M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 15257–15269. Curran Associates, Inc., 2021. URL https://proceedings.neurips.cc/paper_files/paper/2021/file/812214fb8e7066bfa6e32c626c2c688b-Paper.pdf.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up