Research map / Probabilistic and scientific modeling / Dynamical systems
Learning Dynamics of Linear Denoising Autoencoders
Arnu Pretorius, Steve Kroon, Herman Kamper
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Increase input noise | Scalar linear DAE · Scalar setting, λ = 1 | convergence speed | Improved |
| Increase input noise | Scalar linear DAE · Scalar setting, λ = 1 | fixed-point mapping: 1 -> 0.5 -> 1/6 | Hurt |
| Use noise regularization instead of equivalent weight decay | Linear autoencoder · Scalar dynamics | training time | Improved |
| Apply input noise | Linear DAE · MNIST | learning time | Improved |
| Use weight decay instead of input noise | Linear autoencoder · CIFAR-10 | learning time | Hurt |
| Use noise regularization instead of weight decay | ReLU autoencoder · MNIST and CIFAR-10 | learning time | Improved |
| Use noise regularization instead of weight decay | Tanh autoencoder · MNIST and CIFAR-10 | learning dynamics | Mixed |
Closest papers by meaning
- Deconstructing Denoising Diffusion Models for Self-Supervised Learning (ICLR 2025 · similarity 0.89)
- Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training (NeurIPS 2025 · similarity 0.86)
- Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning (NeurIPS 2026 · similarity 0.86)
- Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling (NeurIPS 2025 · similarity 0.86)
- Denoising Autoregressive Representation Learning (ICML 2024 · similarity 0.86)
- Denoising Task Difficulty-based Curriculum for Training Diffusion Models (ICLR 2025 · similarity 0.85)
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.
