Size-free generalization bounds for convolutional neural networks
By Philip M. Long, Hanie Sedghi. 2019
27 citations recorded by the source corpus.
Subfields: Model Architectures, Statistical Learning Theory
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Model Architectures
- Behnam Neyshabur
- Niladri S. Chatterji
- Joan Bruna
- Zalan Fabian
- M. Soltanolkotabi
- Samet Oymak
- Mingchen Li
- Levent Sagun
In Statistical Learning Theory
- Samet Oymak
- M. Soltanolkotabi
- Mingchen Li
- Zalan Fabian
- Behnam Neyshabur
- Colin Wei
- Niladri S. Chatterji
- Tengyu Ma
Citations in the corpus
- Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian (2019, methodology): “See also [43] for improvements via leveraging various properties of the inter-layer Jacobian and [39] for results with convolutional networks.”
- Fantastic Generalization Measures and Where to Find Them (2019, background): “…have attempted to understand the generalization phenomenon in deep models from a theoretical perspective e.g. (Neyshabur et al., 2015b; Bartlett et al., 2017; Neyshabur et al., 2018a; Golowich et al., 2017; Arora et al., 2018; Nagarajan and Kolter, 2019a; Wei and Ma, 2019a; Long and Sedghi, 2019).”
- Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin (2019, background): “Long and Sedghi [2019] prove bounds for convolutional networks which scale with the number of parameters and their distance from initialization.”
- Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias (2019, background): “[27, 26] obtain specific generalisation bounds for CNN architectures.”
- The intriguing role of module criticality in the generalization of deep networks (2019, methodology): “The quantity SoSP was proposed by Long and Sedghi (2019). For the last two measures, we calculate σi and αi as per Definition 3.”