Research map / Optimization / Nonconvex and smooth optimization
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
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 SSAG instead of SGD | Logistic regression with dropout · avazu-app and kddb | training objective convergence | Helped |
| Use S-SAGA instead of S-MISO | Logistic regression with dropout · avazu-app and kddb | training objective convergence | Helped |
| Use SSAG instead of S-MISO | Logistic regression with dropout · avazu-app and kddb | additional memory | Helped |
| Add iterate averaging (ablation) | SGD, S-MISO, and SSAG · Logistic regression with dropout | training objective convergence | Helped |
| Add iterate averaging (ablation) | S-SAGA · Logistic regression with dropout | training objective convergence | Helped |
| Increase dropout probability (ablation) | S-SAGA · avazu-app logistic regression | convergence robustness | No clear effect |
| Increase dropout probability (ablation) | S-MISO · avazu-app logistic regression | convergence | Hurt |
| Use IA-SSAG instead of the other compared methods | AUC maximization with dropout · kddb | AUC | Helped |
| Use IA-SSAG instead of SGD or SSAG | AUC maximization with dropout · avazu-app | AUC | Mixed |
Closest papers by meaning
- Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure (NeurIPS 2017 · similarity 0.91)
- A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates (ICML 2018 · similarity 0.87)
- A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms (ICML 2026 · similarity 0.87)
- Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability (AAAI 2022 · similarity 0.87)
- Demystifying SGD with Doubly Stochastic Gradients (ICML 2024 · similarity 0.87)
- Efficient Stochastic Approximation of Minimax Excess Risk Optimization (ICML 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.