Towards a mathematical understanding of learning from few examples with nonlinear feature maps
Not on the map. Why?
Abstract (arXiv)
We consider the problem of data classification where the training set consists of just a few data points. We explore this phenomenon mathematically and reveal key relationships between the geometry of an AI model's feature space, the structure of the underlying data distributions, and the model's generalisation capabilities. The main thrust of our analysis is to reveal the influence on the model's generalisation capabilities of nonlinear feature transformations mapping the original data into high, and possibly infinite, dimensional spaces.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 7 Nov 2022.
Builds on
13 of 25 references.
References · 13
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2016Understanding deep learning requires rethinking generalizationcited by 1,674
- 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
- 2019Benign Overfitting in Linear Regressioncited by 549
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2018Blessing of dimensionality: mathematical foundations of the statistical physics of datacited by 55
- 2022Benign, Tempered, or Catastrophic: A Taxonomy of Overfittingcited by 36
- 2021High-dimensional separability for one- and few-shot learningcited by 11
- 2017Stochastic Separation Theoremscited by 10
- 2021Demystification of Few-shot and One-shot Learningcited by 10
1 more
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.