Research map / Optimization / Implicit bias and generalization
Regularized linear autoencoders recover the principal components, eventually
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use non-uniform instead of uniform l2 regularization (ablation) | linear autoencoder · MNIST k=20 | distance to axis-aligned solution | Helped |
| use rotation augmented gradient (RAG) instead of non-uniform l2 regularization | linear autoencoder with Nesterov GD · MNIST k=20 | convergence speed to axis-alignment | Helped |
| use RAG instead of regularized objectives as latent dimension grows | linear autoencoder with Nesterov GD · synthetic data m=1000 | epochs to reach 0.3 axis-alignment distance | Helped |
| switch from Nesterov GD to Adam for regularized objectives | non-uniform l2 and nested dropout LAEs · MNIST k=20 | convergence speed | Mixed |
Closest papers by meaning
- Supervised autoencoders: Improving generalization performance with unsupervised regularizers (NeurIPS 2018 · similarity 0.90)
- Loss Landscapes of Regularized Linear Autoencoders (ICML 2019 · similarity 0.90)
- On the Value of Infinite Gradients in Variational Autoencoder Models (NeurIPS 2021 · similarity 0.88)
- Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel (NeurIPS 2019 · similarity 0.88)
- Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders (ICML 2025 · similarity 0.86)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.