Research map / Optimization / Nonconvex and smooth optimization
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
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 |
|---|---|---|---|
| Bregman SGD with constant step size, interpolation setting (zero gradient noise at optimum) | BSGD · Poisson inverse problem (interpolation) | suboptimality | Helped |
| Variance reduction (Bregman SAGA) vs plain BSGD | BSAGA · Tomographic reconstruction | suboptimality | Helped |
| Variance reduction (Bregman SAGA) vs plain BSGD | BSAGA · Distributed optimization (RCV1) | suboptimality | Helped |
| Stochastic updates (BSGD) instead of full Bregman gradient (BGD) | BSGD · Tomographic reconstruction | suboptimality | Helped |
| Bregman SGD constant step size on Poisson problem with noise-free data | BSGD · Poisson inverse problem | suboptimality | Helped |
Closest papers by meaning
- Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization (NeurIPS 2022 · similarity 0.90)
- Stochastic Bias-Reduced Gradient Methods (NeurIPS 2021 · similarity 0.90)
- Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization (ICML 2019 · similarity 0.89)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.89)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (NeurIPS 2025 · similarity 0.88)
- High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise (ICML 2024 · 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.