Research map / Optimization / Nonconvex and smooth optimization
Sparse Training with Lipschitz Continuous Loss Functions and a Weighted Group L0-norm Constraint
Michael R. Metel
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 SPA (randomized smoothing) instead of projected mini-batch SGD | LeNet-5 type net, group l0 constraint · MNIST and FashionMNIST, s in {0.65, 0.5} | test accuracy and training loss | No clear effect |
| increase sparsity level to s = 0.7 | LeNet-5 type net, group l0 constraint · MNIST and FashionMNIST | trainability (layer collapse) | Hurt |
| add sparsity constraint to unconstrained SGD | SPA and PSGD · MNIST and FashionMNIST | test accuracy in later epochs | No clear effect |
| decrease kappa | SPA constants · MNIST and FashionMNIST | estimated L0 and Q constants | Improved |
Closest papers by meaning
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · similarity 0.88)
- Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations (ICLR 2024 · similarity 0.88)
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (ICLR 2024 · similarity 0.88)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.87)
- Delving into the Convergence of Generalized Smooth Minimax Optimization (ICML 2024 · similarity 0.87)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (NeurIPS 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.
