Spectral machine learning
In this thesis we develop a spectral approach to large kernel matrices, graphs and the Hessians of neural networks. This approach paves the way for efficient and improved inference schemes, novel algorithms and theoretical results. The first contribution of the thesis is the development of a novel M...
| Autor Principal: | |
|---|---|
| Outros autores: | |
| Formato: | Thesis |
| Idioma: | English |
| Publicado: |
2020
|
| Subjects: |