Abstract
Projection-free algorithms for bandit convex optimization have received increasing attention, due to the ability to deal with the bandit feedback and complicated constraints simultaneously. The state-of-the-art ones can achieve an expected regret bound of \(O(T^{3/4})\). However, they need to utilize a blocking technique, which is unsatisfying in practice due to the delayed reaction to the change of functions, and results in a logarithmically worse high-probability regret bound of \(O(T^{3/4}\sqrt{\log T})\). In this paper, we study the special case of bandit convex optimization over strongly convex sets, and present a projection-free algorithm, which keeps the \(O(T^{3/4})\) expected regret bound without employing the blocking technique. More importantly, we prove that it can enjoy an \(O(T^{3/4})\) high-probability regret bound, which removes the logarithmical factor in the previous high-probability regret bound. Furthermore, empirical results on synthetic and real-world datasets have demonstrated the better performance of our algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Although Wan et al. [29] originally establish such bound for a decentralized variant of BBCG, it is easy to extend this result for BBCG.
- 2.
References
Abernethy, J., Hazan, E., Rakhlin, A.: Competing in the dark: an efficient algorithm for bandit linear optimization. In: Proceedings of the 21st Conference on Learning Theory, pp. 263–274 (2008)
Agarwal, A., Dekel, O., Xiao, L.: Optimal algorithms for online convex optimization with multi-point bandit feedback. In: Proceedings of the 23rd Conference on Learning Theory, pp. 28–40 (2010)
Awerbuch, B., Kleinberg, R.: Online linear optimization and adaptive routing. J. Comput. Syst. Sci. 74(1), 97–114 (2008)
Bubeck, S., Cesa-Bianchi, N., Kakade, S.M.: Towards minimax policies for online linear optimization with bandit feedback. In: Proceedings of the 25th Conference on Learning Theory, pp. 41.1–41.14 (2012)
Bubeck, S., Dekel, O., Koren, T., Peres, Y.: Bandit convex optimization: \(\sqrt{t}\) regret in one dimension. In: Proceedings of the 28th Conference on Learning Theory, pp. 266–278 (2015)
Bubeck, S., Eldan, R., Lee, Y.T.: Kernel-based methods for bandit convex optimization. In: Proceedings of the 49th Annual ACM Symposium on Theory of Computing, pp. 72–85 (2019)
Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(27), 1–27 (2011)
Chen, L., Harshaw, C., Hassani, H., Karbasi, A.: Projection-free online optimization with stochastic gradient: from convexity to submodularity. In: Proceedings of the 35th International Conference on Machine Learning, pp. 814–823 (2018)
Chen, L., Zhang, M., Karbasi, A.: Projection-free bandit convex optimization. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, pp. 2047–2056 (2019)
Dekel, O., Eldan, R., Koren, T.: Bandit smooth convex optimization: Improving the bias-variance tradeoff. In: Advances in Neural Information Processing Systems 28, pp. 2926–2934 (2015)
Flaxman, A.D., Kalai, A.T., McMahan, H.B.: Online convex optimization in the bandit setting: gradient descent without a gradient. In: Proceedings of the 16th Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 385–394 (2005)
Frank, M., Wolfe, P.: An algorithm for quadratic programming. Naval Res. Logistics Quart. 3(1–2), 95–110 (1956)
Garber, D., Hazan, E.: Faster rates for the frank-wolfe method over strongly-convex sets. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 541–549 (2015)
Garber, D., Hazan, E.: A linearly convergent conditional gradient algorithm with applications to online and stochastic optimization. SIAM J. Optim. 26(3), 1493–1528 (2016)
Garber, D., Kretzu, B.: Improved regret bounds for projection-free bandit convex optimization. In: Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, pp. 2196–2206 (2020)
Garber, D., Kretzu, B.: New projection-free algorithms for online convex optimization with adaptive regret guarantees. In: Proceedings of the 35th Conference on Learning Theory, pp. 2326–2359 (2022)
Garber, D., Kretzu, B.: Projection-free online exp-concave optimization. In: Proceedings of the 36th Conference on Learning Theory (2023)
Hazan, E.: Introduction to online convex optimization. Found. Trends Optim. 2(3–4), 157–325 (2016)
Hazan, E., Kale, S.: Projection-free online learning. In: Proceedings of the 29th International Conference on Machine Learning, pp. 1843–1850 (2012)
Hazan, E., Levy, K.Y.: Bandit convex optimization: towards tight bounds. In: Advances in Neural Information Processing Systems 27, pp. 784–792 (2014)
Hazan, E., Minasyan, E.: Faster projection-free online learning. In: Proceedings of the 33rd Conference on Learning Theory, pp. 1877–1893 (2020)
Ito, S.: An optimal algorithm for bandit convex optimization with strongly-convex and smooth loss. In: Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, pp. 2229–2239 (2020)
Jaggi, M.: Revisiting Frank-Wolfe: projection-free sparse convex optimization. In: Proceedings of the 30th International Conference on Machine Learning, pp. 427–435 (2013)
Kalhan, D.S., et al.: Dynamic online learning via frank-wolfe algorithm. IEEE Trans. Signal Process. 69, 932–947 (2021)
Kretzu, B., Garber, D.: Revisiting projection-free online learning: the strongly convex case. In: Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, pp. 3592–3600 (2021)
McMahan, H.B., et al.: Ad click prediction: a view from the trenches. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1222–1230 (2013)
Saha, A., Tewari, A.: Improved regret guarantees for online smooth convex optimization with bandit feedback. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, pp. 636–642 (2011)
Shalev-Shwartz, S., Singer, Y.: A primal-dual perspective of online learning algorithm. Mach. Learn. 69(2–3), 115–142 (2007)
Wan, Y., Tu, W.W., Zhang, L.: Projection-free distributed online convex optimization with \(\cal{O}(\sqrt{T})\) communication complexity. In: Proceedings of the 37th International Conference on Machine Learning, pp. 9818–9828 (2020)
Wan, Y., Wang, G., Tu, W.W., Zhang, L.: Projection-free distributed online learning with sublinear communication complexity. J. Mach. Learn. Res. 23(172), 1–53 (2022)
Wan, Y., Xue, B., Zhang, L.: Projection-free online learning in dynamic environments. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence Advances, pp. 10067–10075 (2021)
Wan, Y., Zhang, L.: Projection-free online learning over strongly convex set. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence Advances, pp. 10076–10084 (2021)
Wan, Y., Zhang, L., Song, M.: Improved dynamic regret for online frank-wolfe. In: Proceedings of the 36th Conference on Learning Theory (2023)
Wang, Y., Wan, Y., Zhang, S., Zhang, L.: Distributed projection-free online learning for smooth and convex losses. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence, pp. 10226–10234 (2023)
Wang, Y., et al.: Non-stationary projection-free online learning with dynamic and adaptive regret guarantees. ArXiv e-prints arXiv:2305.11726 (2023)
Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the 20th International Conference on Machine Learning, pp. 928–936 (2003)
Acknowledgments
This work was supported by State Grid science and technology project (5700-202327286A-1-1-ZN).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, C., Wang, Y., Tian, P., Cheng, X., Wan, Y., Song, M. (2024). Projection-Free Bandit Convex Optimization over Strongly Convex Sets. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14647. Springer, Singapore. https://doi.org/10.1007/978-981-97-2259-4_9
Download citation
DOI: https://doi.org/10.1007/978-981-97-2259-4_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2261-7
Online ISBN: 978-981-97-2259-4
eBook Packages: Computer ScienceComputer Science (R0)