Research map / Optimization / Optimizers
Learning Sparse Neural Networks through L_0 Regularization
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 |
|---|---|---|---|
| apply hard-concrete L0 regularization | WRN-28-10 with dropout-style hidden-layer gates · CIFAR-10 | test error (%): 3.89 -> 3.83 | Helped |
| apply hard-concrete L0 regularization | WRN-28-10 with dropout-style hidden-layer gates · CIFAR-100 | test error (%): 18.85 -> 18.75 | Helped |
| increase λ from 0.001/N to 0.002/N (ablation) | WRN-28-10-L0hc · CIFAR-10 | test error (%): 3.83 -> 3.93 | Hurt |
| increase λ from 0.001/N to 0.002/N (ablation) | WRN-28-10-L0hc · CIFAR-100 | test error (%): 18.75 -> 19.04 | Hurt |
| use separate λ values by layer (ablation) | MLP 784-300-100 with L0hc · MNIST | test error (%): 1.4 -> 1.8 | Hurt |
| use separate λ values by layer (ablation) | LeNet-5-Caffe with L0hc · MNIST | test error (%): 0.9 -> 1.0 | Hurt |
Closest papers by meaning
- Learning sparse neural networks via sensitivity-driven regularization (NeurIPS 2018 · similarity 0.91)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.90)
- Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries (ICLR 2025 · similarity 0.89)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.88)
- Generalization Bounds for Rank-sparse Neural Networks (NeurIPS 2025 · similarity 0.88)
- Grokking Beyond the Euclidean Norm of Model Parameters (ICML 2025 · 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.