Research map / Optimization / Optimizers
Fast and Accurate Stochastic Gradient Estimation
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 |
|---|---|---|---|
| replace uniform sampling with LSH-based adaptive sampling (LGD) | SGD · YearPredictionMSD, Slice, UJIIndoorLoc linear regression | training loss vs wall-clock time | Helped |
| replace uniform sampling with LSH-based adaptive sampling (LGD) | SGD · YearPredictionMSD, Slice | training loss vs epochs | Helped |
| add LGD sampling on top of AdaGrad | AdaGrad · YearPredictionMSD, Slice | training loss vs wall-clock time | Helped |
| use LGD sampling in BERT fine-tuning instead of uniform sampling | BERT-base · MRPC, RTE | test accuracy/loss vs epochs | Helped |
| LGD sampled points vs uniform samples | SGD gradient estimator · YearPredictionMSD, Slice | gradient L2 norm and cosine similarity to true gradient | Helped |
Closest papers by meaning
- Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates (NeurIPS 2019 · similarity 0.89)
- Adaptive Sampling for SGD by Exploiting Side Information (ICML 2016 · similarity 0.89)
- Stochastic Gradient Descent under Markovian Sampling Schemes (ICML 2023 · similarity 0.89)
- A Variational Analysis of Stochastic Gradient Algorithms (ICML 2016 · similarity 0.88)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.88)
- On the Convergence of Loss and Uncertainty-based Active Learning Algorithms (NeurIPS 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.