Research map / Optimization / Nonconvex and smooth optimization
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep 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 |
|---|---|---|---|
| Train the dense network with BCD instead of a Caffe SGD-based solver | MNIST network with three hidden layers · MNIST | test-set classification error | Helped |
| Train a sparse network with BCD-S instead of a Caffe SGD-based solver | MNIST network with three hidden layers · MNIST | test-set classification error | Helped |
| Use sparse-learning constraints instead of dense learning (ablation) | BCD · MNIST | classification accuracy: 1.34% lower | Hurt |
| Use sparse-learning constraints instead of dense learning (ablation) | BCD · MNIST | nonzero weights: 97.15% -> 2.42% | Helped |
| Use BCD instead of the ADMM-based method | Supervised hashing network · MNIST supervised hashing | training time: about 9 hours -> within 1 hour | Helped |
| Use BCD instead of the ADMM-based method | Supervised hashing network · MNIST supervised hashing | precision, recall, and mAP | Helped |
| Use BCD instead of the ADMM-based method | Supervised hashing network · CIFAR-10 supervised hashing | training time | Helped |
Closest papers by meaning
- Global Convergence of Block Coordinate Descent in Deep Learning (ICML 2019 · similarity 0.94)
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima (NeurIPS 2025 · similarity 0.93)
- A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks (ICLR 2019 · similarity 0.88)
- On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths (ICML 2021 · similarity 0.87)
- Learning Provably Improves the Convergence of Gradient Descent (NeurIPS 2025 · similarity 0.86)
- Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods (ICLR 2025 · similarity 0.85)
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.