Mathematical Perspective of Machine Learning
Not on the map. Why?
Abstract (arXiv)
We take a closer look at some theoretical challenges of Machine Learning as a function approximation, gradient descent as the default optimization algorithm, limitations of fixed length and width networks and a different approach to RNNs from a mathematical perspective.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 1; 2025: 3; 2026: 1.
5 papers.
- 2024An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learningcited by 6
- 2025Convergence for adaptive resampling of random Fourier featurescited by 1
- 2025Finite Samples for Shallow Neural Networkscited by 0
- 2025Cluster-Based Generalized Additive Models Informed by Random Fourier Featurescited by 0
- 2026Non-asymptotic estimates of the minimal risk in statistical learningcited by 0
- 2026Non-asymptotic estimates of the minimal risk in statistical learning22 Jun 2026
- 2025Cluster-Based Generalized Additive Models Informed by Random Fourier Features22 Dec 2025
- 2025Convergence for adaptive resampling of random Fourier features3 Sep 2025
- 2025Finite Samples for Shallow Neural Networks17 Mar 2025
- 2024An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learning23 Aug 2024