Research map / Optimization / Implicit bias and generalization
On Dropout and Nuclear Norm Regularization
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 |
|---|---|---|---|
| Train with dropout and increase the dropout rate | Deep linear networks · Synthetic regression | singular-value spectrum | Helped |
| Train with dropout and increase the dropout rate | Deep linear networks · Synthetic regression | network-map rank | Helped |
| Train with dropout | Deep linear networks with one output neuron · Synthetic regression | normalized equalization gap | Helped |
Closest papers by meaning
- On the Regularization Properties of Structured Dropout (CVPR 2020 · similarity 0.91)
- Dropout: Explicit Forms and Capacity Control (ICML 2021 · similarity 0.90)
- The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization (NeurIPS 2021 · similarity 0.89)
- Dropout as a Structured Shrinkage Prior (ICML 2019 · similarity 0.89)
- Dropout with Expectation-linear Regularization (ICLR 2017 · similarity 0.88)
- Nuclear Norm Regularization for Deep Learning (NeurIPS 2024 · 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.