Research map / Optimization / Nonconvex and smooth optimization
Global Convergence of Block Coordinate Descent in Deep Learning
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 proximal updates for non-strongly convex subproblems | Two-splitting and three-splitting BCD for DNN training · DNN training | average squared subgradient norm: O(1/K) | Helped |
| Use activations Lipschitz continuous on bounded sets and handle the BCD updates accordingly | Two-splitting and three-splitting BCD for DNN training · DNN training | average squared subgradient norm: O(1/K) | Helped |
| Use a prox-linear output-state update with a smooth loss having Lipschitz continuous gradient | Two-splitting and three-splitting BCD · DNN training with smooth loss | average squared subgradient norm: O(1/K) | Helped |
| Adapt three-splitting BCD to residual-layer constraints | ResNet three-splitting BCD · ResNet training | average squared subgradient norm: O(1/K) | Helped |
Closest papers by meaning
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima (NeurIPS 2025 · similarity 0.95)
- Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks (NeurIPS 2017 · similarity 0.94)
- A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks (ICLR 2019 · similarity 0.90)
- On the Global Convergence of Training Deep Linear ResNets (ICLR 2020 · similarity 0.89)
- On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths (ICML 2021 · similarity 0.89)
- On the Unstable Convergence Regime of Gradient Descent (AAAI 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.