We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| danielkunin/Regularized-Linear-Autoencoders | canonical | 1 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| LAE_PCA_untied | Ran | danielkunin/Regularized-Linear-Autoencoders/algorithms_visualize.py pointer only (licence: NONE) · get_code("940ab2d839b315fe") |
| LAE_PCA_exact | Not yet run | danielkunin/Regularized-Linear-Autoencoders/algorithms_visualize.py pointer only (licence: NONE) · get_code("23964c4b410b0ca1") |
| LAE_PCA_tied | Not yet run | danielkunin/Regularized-Linear-Autoencoders/algorithms_visualize.py pointer only (licence: NONE) · get_code("0a51346b616145ef") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but cannot learn the principal directions themselves. In this paper, we prove that $L_2$-regularized LAEs are symmetric at all critical points and learn the principal directions as the left singular vectors of the decoder. We smoothly parameterize the critical manifold and relate the minima to the MAP estimate of probabilistic PCA. We illustrate these results empirically and consider implications for PCA algorithms, computational neuroscience, and the algebraic topology of learning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1901.08168")
get_code_for_paper("1901.08168")
have("1901.08168")
Connect an agent — have() is free.