Research map / Optimization / Implicit bias and generalization
Implicit Regularization of Dropout
Zhongwang Zhang, Zhi‐Qin John Xu
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 |
|---|---|---|---|
| add dropout | FNN · MNIST | test accuracy: 98.1% -> 98.7% | Improved |
| add dropout | VGG-9 · CIFAR-10 (first 2048 examples) | test accuracy: 59.2% -> 60.6% | Improved |
| add dropout | ResNet-20 · CIFAR-100 | test accuracy: 34.1% -> 54.7% | Improved |
| add dropout | Transformer · Multi30k | test accuracy: 34.7% -> 49.3% | Improved |
| add explicit R1 regularization term to the loss instead of dropout (ablation) | two-layer FNN · MNIST (first 1000 images) | test accuracy | Improved |
| add explicit R2 (gradient-norm) term to full-batch GD (ablation) | FNN · MNIST (first 1000 images) | test accuracy | No clear effect |
Closest papers by meaning
- The Implicit and Explicit Regularization Effects of Dropout (ICML 2020 · similarity 0.94)
- Dropout Reduces Underfitting (ICML 2023 · similarity 0.92)
- On the Regularization Properties of Structured Dropout (CVPR 2020 · similarity 0.92)
- Demystifying Dropout (ICML 2019 · similarity 0.91)
- Stochastic Modified Equations and Dynamics of Dropout Algorithm (ICLR 2024 · similarity 0.90)
- Estimating Implicit Regularization in Deep Learning (NeurIPS 2026 · similarity 0.88)
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.
