A Theory of PAC Learnability of Partial Concept Classes-Reference-Cited by-同舟云学术

A Theory of PAC Learnability of Partial Concept Classes

Published:2022-02 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS)
language:
Short-container-title:

Author:

Alon Noga¹,Hanneke Steve²,Holzman Ron³,Moran Shay³

Affiliation:

1. Princeton University,NJ,USA

2. Purdue University,West Lafayette,IN,USA

3. Technion,Haifa,Israel

Funder

NSF

BSF

Simons Foundation

ISF

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9719594/9719683/09719837.pdf?arnumber=9719837

Reference56 articles.

1. Deep double descent: Where bigger models and more data hurt;nakkiran;8th International Conference on Learning Representations ICLR 2020,2020

2. Uniform convergence may be unable to explain generalization in deep learning;nagarajan;Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019,2019

3. Nearest-neighbor sample compression: Efficiency, consistency, infinite dimensions;kontorovich;Advances in Neural Information Processing Systems 30 Annual Conference on Neural Information Processing Systems 2017,2017

4. Model Theory

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Optimal PAC Bounds without Uniform Convergence;2023 IEEE 64th Annual Symposium on Foundations of Computer Science (FOCS);2023-11-06

2. A Characterization of List Learnability;Proceedings of the 55th Annual ACM Symposium on Theory of Computing;2023-06-02

3. A Borsuk-Ulam Lower Bound for Sign-Rank and Its Applications;Proceedings of the 55th Annual ACM Symposium on Theory of Computing;2023-06-02