Research map / Optimization / Optimizers
Efficiency Ordering of Stochastic Gradient Descent
Jie Hu, Vishwaraj Doshi, Do Young Eun
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 a non-backtracking random walk instead of a simple random walk | SGD · General graphs | asymptotic covariance (Loewner order) | Improved |
| Use a non-backtracking random walk instead of a simple random walk | SGD · Dolphins; logistic regression and sum-of-non-convex-functions | MSE | Improved |
| Use single shuffling instead of i.i.d. sampling | SGD · General objective functions | asymptotic covariance (Loewner order) | Improved |
| Use random shuffling instead of i.i.d. sampling | SGD · General objective functions | asymptotic covariance (Loewner order) | Improved |
| Use single shuffling instead of uniform sampling | SGD · Dolphins; logistic regression and sum-of-non-convex-functions | MSE | Improved |
| Use random shuffling instead of uniform sampling | SGD · Dolphins; logistic regression and sum-of-non-convex-functions | MSE | Improved |
| Drive SGD with an input sequence that is more efficient under asymptotic variance ordering | SGD · Same stationary distribution; asymptotic regime | iterate covariance (Loewner order) | Improved |
| Choose a chain with smaller SLEM rather than one with better efficiency ordering | Random-walk SGD · Two graph simulations described in the introduction | MSE | Hurt |
| Use a more efficient chain despite having the same SLEM | Random-walk SGD · Graph simulation described in the introduction | MSE | Improved |
| Use a more efficient noise sequence | Nesterov accelerated SGD and Adam · Additional numerical simulations | error | Improved |
Closest papers by meaning
- Stochastic Gradient Descent under Markovian Sampling Schemes (ICML 2023 · similarity 0.89)
- Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective (NeurIPS 2024 · similarity 0.88)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.87)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · similarity 0.87)
- SGD with memory: fundamental properties and stochastic acceleration (ICLR 2025 · similarity 0.86)
- On Convergence of Incremental Gradient for Non-convex Smooth Functions (ICML 2024 · similarity 0.86)
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.
