Research map / Optimization / Optimizers
SGD: General Analysis and Improved Rates
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 |
|---|---|---|---|
| switch from a constant to a decreasing stepsize | SGD with uniform single-element sampling · Ridge regression and regularized logistic regression | relative error | Helped |
| switch from a constant to a decreasing stepsize | SGD for PCA · PCA | relative error | Helped |
| use the theoretically optimal minibatch size | SGD minibatch sampling · Logistic regression | convergence | Helped |
| use importance sampling instead of uniform sampling | single-element and independent-sampling SGD · Logistic regression | convergence | Mixed |
| increase minibatch size to τ=n/5 | SGD with τ-nice or τ-independent sampling · PCA | convergence | Helped |
| use the theoretically optimal minibatch size τ* | SGD minibatch sampling · PCA | convergence | Helped |
| use minibatch sampling instead of single-element sampling | SGD · PCA | convergence | Helped |
Closest papers by meaning
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.90)
- Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective (NeurIPS 2024 · similarity 0.90)
- Demystifying SGD with Doubly Stochastic Gradients (ICML 2024 · similarity 0.90)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.89)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.89)
- SGD with memory: fundamental properties and stochastic acceleration (ICLR 2025 · 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.