Research map / Learning theory and algorithms / Sample complexity
Stochastic $L^\natural$-convex Function Minimization
Haixiang Zhang, Zeyu Zheng, Javad Lavaei
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 |
|---|---|---|---|
| add truncation step to projected SSGD (ablation) | Algorithm 2 · Staffing allocation regularized d=4 N=10 | cost: 6.56e5 -> 2.99e5 | Improved |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation regularized d=24 N=10 | cost: 3.09e7 -> 1.50e7 | Improved |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation constrained d=4 N=10 | cost: 4.99e5 -> 3.00e5 | Improved |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation constrained d=24 N=10 | cost: 2.10e7 -> 1.36e7 | Improved |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation regularized d=4 N=50 | cost: 1.08e5 -> 5.34e4 | Improved |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation regularized d=4 N=10 | objective value: 2.11e2 -> 2.10e2 | No clear effect |
| add truncation step (ablation) | Algorithm 2 · Staffing allocation constrained d=24 N=10 | objective value: 1.17e1 -> 9.43e0 | Mixed |
| increase dimension d from 2 to 20 at N=50 | Truncated subgradient · Separable convex | cost (x10^7): 0.39 -> 1.69 | Hurt |
| increase dimension d from 2 to 20 at N=50 | Dimension reduction · Separable convex | cost (x10^7): 0.19 -> 4.28 | Hurt |
| use dimension reduction instead of truncated subgradient, low d | Dimension reduction · Separable convex d=2 N=50 | cost (x10^7): 0.39 -> 0.19 | Improved |
| use dimension reduction instead of truncated subgradient, high d | Dimension reduction · Separable convex d=20 N=50 | cost (x10^7): 1.69 -> 4.28 | Hurt |
| increase N from 50 to 150 at d=2 | Dimension reduction · Separable convex | cost (x10^7): 0.19 -> 0.25 | No clear effect |
Closest papers by meaning
- Optimal approximation for unconstrained non-submodular minimization (ICML 2020 · similarity 0.90)
- Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization (JMLR 2020 · similarity 0.90)
- Stochastic Weakly Convex Optimization beyond Lipschitz Continuity (ICML 2024 · similarity 0.88)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.88)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.87)
- Discrete and Continuous Difference of Submodular Minimization (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.
