Research map / Optimization / Nonconvex and smooth optimization
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
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 SPD1 instead of PSGD | Regularized logistic regression · Synthetic data, n=1000, d=100 | primal sub-optimality | Hurt |
| Use SPD1-VR instead of SVRG and SAGA | Regularized logistic regression · Synthetic data, n=1000, d=100 | primal sub-optimality | Hurt |
| Use SPD1 instead of PSGD | Regularized logistic regression · Synthetic data, n=1000, d=1000 | primal sub-optimality | No clear effect |
| Use SPD1-VR instead of SVRG and SAGA | Regularized logistic regression · Synthetic data, n=1000, d=1000 | primal sub-optimality | Helped |
| Use SPD1 instead of PSGD | Regularized logistic regression · Synthetic data, n=1000, d=10000 | primal sub-optimality | Helped |
| Use SPD1-VR instead of SVRG and SAGA | Regularized logistic regression · Synthetic data, n=1000, d=10000 | primal sub-optimality | Helped |
| Use SPD1 instead of PSGD | Regularized logistic regression · colon-cancer | primal sub-optimality | Helped |
| Use SPD1-VR instead of competing methods | Regularized logistic regression · colon-cancer | primal sub-optimality | Helped |
| Use SPD1 instead of PSGD | Regularized logistic regression · gisette | primal sub-optimality | Hurt |
| Use SPD1-VR instead of competing methods | Regularized logistic regression · gisette | primal sub-optimality | Helped |
| Use SPD1 instead of PSGD | Regularized logistic regression · rcv1.binary | primal sub-optimality | Helped |
| Use SPD1-VR instead of SVRG and SAGA | Regularized logistic regression · rcv1.binary | primal sub-optimality | Helped |
Closest papers by meaning
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization (NeurIPS 2017 · similarity 0.92)
- Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization (ICML 2017 · similarity 0.91)
- On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks (NeurIPS 2017 · similarity 0.90)
- Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms (ICML 2017 · similarity 0.89)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.87)
- SOREL: A Stochastic Algorithm for Spectral Risks Minimization (ICLR 2025 · similarity 0.86)
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.