Research map / Optimization / Nonconvex and smooth optimization
Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes
Junqi Tang, Mohammad Golbabaee, Francis Bach, Mike E davies
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 scheduled restarts of Katyusha based on restricted strong convexity | Katyusha · Lasso on Madelon, RCV1, REGED | objective gap vs gradient evaluations | Improved |
| use a restart period from an RSC estimate 20x too large or too small instead of the tuned one (ablation) | Rest-Katyusha · Lasso on Madelon, RCV1, REGED | objective gap vs gradient evaluations | Hurt |
| estimate the RSC parameter on the fly to adapt the restart period | Rest-Katyusha · Lasso on Madelon, RCV1, REGED | objective gap vs gradient evaluations | Improved |
Closest papers by meaning
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization (NeurIPS 2017 · similarity 0.89)
- Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations (JMLR 2019 · similarity 0.89)
- Katyusha: The First Direct Acceleration of Stochastic Gradient Methods (JMLR 2018 · similarity 0.88)
- Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients (JMLR 2025 · similarity 0.88)
- A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates (ICML 2018 · similarity 0.88)
- Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions (NeurIPS 2024 · 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.
