Research map / Optimization / Nonconvex and smooth optimization
Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions
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 |
|---|---|---|---|
| Accelerated stochastic mirror descent (ASMD, Algorithm 2) with an explicit/implicit hybrid Euler discretization of the SDE | stochastic mirror descent for strongly convex objectives · synthetic and real-data regression/logistic experiments | log averaged function value gap / convergence speed | Helped |
| Accelerated scheme (ASMD3 with additional sequence) vs. plain SMD | stochastic mirror descent · E2006-tfidf and a9a | convergence speed | Helped |
| Using the proposed ASMD/ASMD3 instead of AC-SA | accelerated stochastic mirror descent · synthetic and real datasets | convergence speed | No clear effect |
Closest papers by meaning
- Acceleration and Averaging in Stochastic Descent Dynamics (NeurIPS 2017 · similarity 0.92)
- Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time (ICML 2026 · similarity 0.90)
- Adaptive Averaging in Accelerated Descent Dynamics (NeurIPS 2016 · similarity 0.90)
- Stochastic Mirror Descent in Variationally Coherent Optimization Problems (NeurIPS 2017 · similarity 0.89)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.88)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · 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.