Evaluated CMI bounds for meta learning: Tightness and expressiveness

F Hellström, G Durisi - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …
被引用次数：13 相关文章

Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

F Hellström, G Durisi - arXiv preprint arXiv:2210.06511, 2022 - arxiv.org
Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …

Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

F Hellström, G Durisi - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …

Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

F Hellström, G Durisi - Advances in Neural Information Processing …, 2022 - openreview.net
Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …

Evaluated CMI bounds for meta learning: tightness and expressiveness

F Hellström, G Durisi - Proceedings of the 36th International Conference …, 2022 - dl.acm.org
Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …