Research map / Optimization / Implicit bias and generalization
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
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 a two-layer linear network instead of a linear model | Least-squares linear autoencoder · Synthetic matrix reconstruction | reconstruction error | Helped |
| Factor the predictor into two trainable linear layers | Two-layer linear network · Least-squares regression | component learning order | Helped |
| Use the linear model rather than the two-layer factorization | Least-squares linear autoencoder · Synthetic matrix reconstruction | reconstruction error | Hurt |
Closest papers by meaning
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.91)
- Implicit Gradient Regularization (ICLR 2021 · similarity 0.91)
- Gradient Flow Dynamics and Implicit Bias of Diagonal Linear Networks under Infinitesimal Initialization (ICML 2026 · similarity 0.89)
- Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer (ICML 2025 · similarity 0.89)
- Deep linear networks for regression are implicitly regularized towards flat minima (NeurIPS 2024 · similarity 0.88)
- Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit (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.