Research map / Optimization / Nonconvex and smooth optimization
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
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 dissipativity and an LMI to analyze SVRG Option I | SVRG Option I · Strongly convex finite-sum objectives | epoch contraction factor | Helped |
| Use averaged inner iterates as the next snapshot | SVRG · Strongly convex finite-sum objectives | epoch contraction factor | Helped |
| Generalize the Katyusha parameter choice to τ2 values other than 1/2 | Katyusha · Strongly convex finite-sum objectives | iteration complexity | No clear effect |
| Use dissipativity supply rates and an LMI to recover convergence guarantees | SVRG and Katyusha · Strongly convex finite-sum objectives | iteration complexity | No clear effect |
| Drop component-function convexity while retaining L-smoothness in the SVRG Option I analysis | SVRG Option I · Strongly convex finite-sum objectives | epoch contraction factor | Mixed |
Closest papers by meaning
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.91)
- A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates (ICML 2018 · similarity 0.90)
- Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots (ICML 2022 · similarity 0.90)
- Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems (ICML 2020 · similarity 0.90)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.88)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.88)
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.