Research map / Optimization / Nonconvex and smooth optimization
Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification
Hoai An Le Thi, Hoai Minh Le, Duy Nhat Phan, Bach Tran
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 |
|---|---|---|---|
| batch size 10% instead of full-batch DCA | SDCA · sensorless | running time: 1.78s | Improved |
| batch size 10% vs best batch size | SDCA · sensorless | accuracy: 85.23% -> 85.30 | No clear effect |
| stochastic SDCA vs full-batch DCA | SDCA · aloi to covertype | running time: 11.6 times (aloi) to 55.1 times (covertype) | Improved |
| SDCA vs DCA | SDCA · covertype, sim 1, sim 3 | accuracy: 0.06% to 0.28% | Improved |
| SDCA vs DCA | SDCA · madelon, sim 2 | accuracy: 1.35% and 3.07% | Improved |
| SDCA vs DCA | SDCA · aloi, sensorless | accuracy: 4.9% | Hurt |
| SDCA vs LibLinear | SDCA · sim 1 | running time: 1532 | Improved |
| SDCA vs LibLinear on sim 1 accuracy | SDCA · sim 1 | accuracy: 72.62 -> 72.24 | Hurt |
| SDCA vs msgl feature selection | SDCA · sim 1 | sparsity: 82% | Improved |
| SDCA vs LibLinear | SDCA · sim 3 | accuracy: 0.89% | Improved |
| SDCA vs LibLinear | SDCA · aloi | running time: 12.6 times | Improved |
| SDCA vs LibLinear and msgl | SDCA · covertype | running time: 45 times faster than LibLinear and 89 times | Improved |
Closest papers by meaning
- Stochastic DCA with Variance Reduction and Applications in Machine Learning (JMLR 2022 · similarity 0.92)
- Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence (ICML 2019 · similarity 0.89)
- Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization (ICML 2018 · similarity 0.86)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.85)
- MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures (ICLR 2025 · similarity 0.84)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.84)
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.
