2000 character limit reached
A Combinatorial Characterization of Supervised Online Learnability
Published 7 Jul 2023 in cs.LG | (2307.03816v2)
Abstract: We study the online learnability of hypothesis classes with respect to arbitrary, but bounded loss functions. No characterization of online learnability is known at this level of generality. We give a new scale-sensitive combinatorial dimension, named the sequential minimax dimension, and show that it gives a tight quantitative characterization of online learnability. In addition, we show that the sequential minimax dimension subsumes most existing combinatorial dimensions in online learning theory.
- Optimal learners for realizable regression: Pac learning and online learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
- Agnostic online learning. In COLT, volume 3, page 1, 2009.
- Learnability can be undecidable. Nature Machine Intelligence, 1(1):44–48, 2019.
- Prediction, learning, and games. Cambridge university press, 2006.
- Multiclass learnability and the erm principle. In Sham M. Kakade and Ulrike von Luxburg, editors, Proceedings of the 24th Annual Conference on Learning Theory, volume 19 of Proceedings of Machine Learning Research, pages 207–232, Budapest, Hungary, 09–11 Jun 2011. PMLR.
- Jürgen Eckhoff. Helly, Radon, and Carathéodory Type Theorems. In Handbook of Convex Geometry, pages 389–448. North-Holland, Amsterdam, 1993. ISBN 978-0-444-89596-7. URL https://www.sciencedirect.com/science/article/pii/B9780444895967500171.
- Optimal prediction using expert advice and randomized littlestone dimension, 2023.
- Multiclass online learning and uniform convergence. Proceedings of the 36th Annual Conference on Learning Theory (COLT), 2023.
- Nick Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318, 1987.
- List online classification. arXiv preprint arXiv:2303.15383, 2023.
- Johann Radon. Mengen konvexer körper, die einen gemeinsamen punkt enthalten. Mathematische Annalen, 83(1-2):113–115, 1921.
- Online learning via sequential complexities. J. Mach. Learn. Res., 16(1):155–186, 2015a.
- Sequential complexities and uniform martingale laws of large numbers. Probability theory and related fields, 161:111–153, 2015b.
- Relax and randomize : From value to algorithms. In F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 25. Curran Associates, Inc., 2012. URL https://proceedings.neurips.cc/paper_files/paper/2012/file/53adaf494dc89ef7196d73636eb2451b-Paper.pdf.
- Online learning with set-valued feedback. arXiv preprint arXiv:2306.06247, 2023.
- Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, USA, 2014.
- On uniform convergence of the frequencies of events to their probabilities. Teoriya Veroyatnostei i ee Primeneniya, 16(2):264–279, 1971.
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.