Research map / Optimization / Implicit bias and generalization
Connecting Optimization and Regularization Paths
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 |
|---|---|---|---|
| early-stop gradient descent at the theoretically derived time t* | gradient descent on linear regression · simulated linear model, p=100, n 100 to 1500 | excess risk | Helped |
| use GD optimum t* versus ridge regression optimum | gradient descent · simulated linear regression | optimal excess risk | No clear effect |
Closest papers by meaning
- The Statistical Complexity of Early-Stopped Mirror Descent (NeurIPS 2020 · similarity 0.91)
- Obtaining Adjustable Regularization for Free via Iterate Averaging (ICML 2020 · similarity 0.88)
- On the Origin of Implicit Regularization in Stochastic Gradient Descent (ICLR 2021 · similarity 0.88)
- Characterizing Implicit Bias in Terms of Optimization Geometry (ICML 2018 · similarity 0.88)
- Implicit Gradient Regularization (ICLR 2021 · similarity 0.88)
- Implicit Sparse Regularization: The Impact of Depth and Early Stopping (NeurIPS 2021 · 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.