Research map / Optimization / Distributed and compressed
Rethinking gradient sparsification as total error minimization
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 Top-k with hard-threshold sparsifier at fixed average density | error-feedback SGD · ResNet-18 CIFAR-10, average density 0.06% | test accuracy (%): 91.1% -> 93.9% | Helped |
| replace Top-k with hard-threshold sparsifier at fixed average density | error-feedback SGD · LSTM on Wikitext, density 0.025% | perplexity: >2 better perplexity | Helped |
| replace Top-k with hard-threshold sparsifier at fixed average density | error-feedback SGD · NCF on Movielens-20M | Hit-Rate@10: >1% better | Helped |
| replace Top-k with hard-threshold sparsifier (fixed threshold, variable k) | error-feedback SGD · Logistic regression gisette | convergence speed and data volume: ~600x less data than SGD at same speed | Helped |
| use hard-threshold instead of ACCORDION adaptive Top-k | adaptive sparsification · CIFAR-10 | accuracy: up to 0.8% better accuracy with 4x fewer bits | Helped |
Closest papers by meaning
- The Convergence of Sparsified Gradient Methods (NeurIPS 2018 · similarity 0.90)
- Gradient Sparsification for Communication-Efficient Distributed Optimization (NeurIPS 2018 · similarity 0.89)
- ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training (NeurIPS 2020 · similarity 0.89)
- Sparse maximal update parameterization: A holistic approach to sparse training dynamics (NeurIPS 2024 · similarity 0.87)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · similarity 0.87)
- A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training (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.