Research map / Optimization / Nonconvex and smooth optimization
Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability
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 |
|---|---|---|---|
| Use every sample sequentially from a single dependent trajectory (SP) | PGD for the lasso-type objective · Autoregressive-process experiment | regret, fixed-point residual, and iterate error | Helped |
| Use every sample sequentially rather than sampling at regular intervals | PGD for the lasso-type objective · Autoregressive-process experiment | computational efficiency | Helped |
| Use multiple replication with trajectory length s=4 (ablation) | PGD for the lasso-type objective · Autoregressive-process experiment | regret, fixed-point residual, and iterate error | Hurt |
| Use multiple replication with small s (ablation) | PGD for the lasso-type objective · Autoregressive-process experiment | regret, fixed-point residual, and iterate error | Hurt |
| Increase the multiple-replication trajectory length across s=4, 6, 8, and 10 (ablation) | PGD for the lasso-type objective · Autoregressive-process experiment | regret, fixed-point residual, and iterate error | Mixed |
| Subsample one trajectory at regular intervals with m=2 or m=3 (ablation) | PGD for the lasso-type objective · Autoregressive-process experiment | computational efficiency | Hurt |
| Apply SAA to dependent samples under the paper's stated mixing and bounded-loss conditions | SAA estimators · Dependent-data stochastic optimization | asymptotic consistency | Helped |
| Use the paper's weakened phi-mixing condition for finite-sample analysis | SAA estimators · Dependent-data stochastic optimization | out-of-sample performance guarantee | Helped |
| Use S-KM with samples from a dependent process | Stochastic first-order algorithms · Dependent-data SAA optimization | approximation error | Helped |
Closest papers by meaning
- Sample Average Approximation for Conditional Stochastic Optimization with Dependent Data (ICML 2024 · similarity 0.92)
- New Sample Complexity Bounds for Sample Average Approximation in Heavy-Tailed Stochastic Programming (ICML 2024 · similarity 0.89)
- A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging (NeurIPS 2025 · similarity 0.88)
- Generalization Analysis of Stochastic Weight Averaging with General Sampling (ICML 2024 · similarity 0.88)
- The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective (NeurIPS 2025 · similarity 0.87)
- How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates? (NeurIPS 2026 · 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.