Research map / Optimization / Optimizers
A Variational Analysis of Stochastic Gradient Algorithms
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 |
|---|---|---|---|
| add diagonal preconditioning to constant SGD (ablation) | constant SGD · Wine | KL divergence: 18.7 -> 14.0 | Helped |
| add diagonal preconditioning to constant SGD (ablation) | constant SGD · Skin | KL divergence: 0.471 -> 0.921 | Hurt |
| add diagonal preconditioning to constant SGD (ablation) | constant SGD · Protein | KL divergence: 1000.9 -> 678.4 | Helped |
| add full-rank preconditioning to constant SGD (ablation) | constant SGD · Wine | KL divergence: 18.7 -> 0.7 | Helped |
| add full-rank preconditioning to constant SGD (ablation) | constant SGD · Skin | KL divergence: 0.471 -> 0.005 | Helped |
| add full-rank preconditioning to constant SGD (ablation) | constant SGD · Protein | KL divergence: 1000.9 -> 1.8 | Helped |
| replace diagonal with full-rank preconditioning (ablation) | constant SGD · Wine | KL divergence: 14.0 -> 0.7 | Helped |
| replace diagonal with full-rank preconditioning (ablation) | constant SGD · Skin | KL divergence: 0.921 -> 0.005 | Helped |
| replace diagonal with full-rank preconditioning (ablation) | constant SGD · Protein | KL divergence: 678.4 -> 1.8 | Helped |
| replace diagonal with full-rank preconditioning (ablation) | SGFS · Protein | KL divergence: 597.4 -> 1.3 | Helped |
Closest papers by meaning
- Asymptotic theory of SGD with a general learning-rate (NeurIPS 2025 · similarity 0.92)
- Robust, Accurate Stochastic Optimization for Variational Inference (NeurIPS 2020 · similarity 0.91)
- Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent (NeurIPS 2023 · similarity 0.91)
- Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks (ICLR 2018 · similarity 0.91)
- Statistical Guarantees for High-Dimensional Stochastic Gradient Descent (NeurIPS 2025 · similarity 0.90)
- Demystifying SGD with Doubly Stochastic Gradients (ICML 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.