Research map / Optimization / Nonconvex and smooth optimization
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
Yuchen Zhang, Lin Xiao
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 |
|---|---|---|---|
| use SPDC instead of batch methods AFG and L-BFGS | SPDC · large lambda | optimality gap vs passes | Improved |
| shrink regularization lambda to 10^-8 | SPDC · real datasets | optimality gap vs passes | Mixed |
| use SPDC instead of SAG and SDCA on ill-conditioned problems | SPDC · synthetic ridge regression | optimality gap vs passes | Improved |
| use SPDC single loop instead of ASDCA inner-outer loop | SPDC · synthetic ridge regression | optimality gap vs passes | Improved |
| use SPDC instead of ASDCA | SPDC · Covtype | optimality gap vs passes | Hurt |
| use SPDC instead of ASDCA | SPDC · RCV1 and News20 | optimality gap vs passes | Improved |
| use SPDC instead of SAG and SDCA at large lambda | SPDC · real datasets | optimality gap vs passes | No clear effect |
Closest papers by meaning
- Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity (NeurIPS 2018 · similarity 0.93)
- Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms (ICML 2017 · similarity 0.92)
- Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization (ICML 2017 · similarity 0.91)
- Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations (JMLR 2019 · similarity 0.90)
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization (NeurIPS 2017 · similarity 0.90)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (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.
