Research map / Optimization / Implicit bias and generalization
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
Quynh N Nguyen, Marco Mondelli
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 |
|---|---|---|---|
| Use one first hidden layer with width N, followed by constant-width pyramidal layers, under the stated initialization conditions | Deep networks trained by gradient descent · Square-loss training data | training loss convergence | Improved |
| Use LeCun initialization and scale the first-layer width as stated | Deep pyramidal networks · Sub-Gaussian training data on the sphere | first-layer width requirement | Mixed |
| Require the activation to be nonlinear | The lower bound on λ_* under LeCun initialization · N ≤ d^k | λ_* lower bound | Improved |
Closest papers by meaning
- The Loss Surface of Deep and Wide Neural Networks (ICML 2017 · similarity 0.90)
- On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths (ICML 2021 · similarity 0.90)
- An Improved Analysis of Training Over-parameterized Deep Neural Networks (NeurIPS 2019 · similarity 0.89)
- A Convergence Theory for Deep Learning via Over-Parameterization (ICML 2019 · similarity 0.89)
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima (NeurIPS 2025 · similarity 0.87)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.87)
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.
