Inferring relevant features: From QFT to PCA
- Title
- Inferring relevant features: From QFT to PCA
- Author
- Beny, Cedric
- Keywords
- Quantum field theory; machine learning; kernel PCA; fisher information metric; Bayesian inference
- Issue Date
- 2018-12
- Publisher
- WORLD SCIENTIFIC PUBL CO PTE LTD
- Citation
- INTERNATIONAL JOURNAL OF QUANTUM INFORMATION, v. 16, No. 8, Article no. 1840012
- Abstract
- In many-body physics, renormalization techniques are used to extract aspects of a statistical or quantum state that are relevant at large scale, or for low energy experiments. Recent works have proposed that these features can be formally identified as those perturbations of the states whose distinguishability most resist coarse-graining. Here, we examine whether this same strategy can be used to identify important features of an unlabeled dataset. This approach indeed results in a technique very similar to kernel PCA (principal component analysis), but with a kernel function that is automatically adapted to the data, or "learned". We test this approach on handwritten digits, and find that the most relevant features are significantly better for classification than those obtained from a simple Gaussian kernel.
- URI
- https://www.worldscientific.com/doi/abs/10.1142/S0219749918400129https://repository.hanyang.ac.kr/handle/20.500.11754/121496
- ISSN
- 0219-7499; 1793-6918
- DOI
- 10.1142/S0219749918400129
- Appears in Collections:
- COLLEGE OF SCIENCE AND CONVERGENCE TECHNOLOGY[E](과학기술융합대학) > APPLIED MATHEMATICS(응용수학과) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML