Research map / Optimization / Nonconvex and smooth optimization
Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
PHUONG_HA NGUYEN, Lam Nguyen, Marten van Dijk
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 the cited diminishing step-size sequences based on μ and L | SGD · Strongly convex and smooth objectives | expected squared distance Y_t: within a factor 32 of the lower bound | Improved |
| Restrict the analysis to SGD with diminishing step sizes and derive a dimension-independent lower bound | SGD on strongly convex objectives · Strongly convex objectives | expected squared distance Y_t: 775·d | Improved |
| Use algorithms beyond classical SGD | Strongly convex optimization · Strongly convex objectives | expected squared distance Y_t: 32·775·d | Mixed |
| Use SGD step sizes based on estimated full gradients or iterate error in addition to global parameters | Extended SGD · Strongly convex and smooth objectives | expected squared distance Y_t | No clear effect |
Closest papers by meaning
- Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD (ICML 2019 · similarity 0.92)
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods (ICLR 2024 · similarity 0.90)
- Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective (NeurIPS 2024 · similarity 0.90)
- Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime (NeurIPS 2025 · similarity 0.90)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.89)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.89)
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.
