Research map / Optimization / Optimizers
AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
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 |
|---|---|---|---|
| Use AutoAssist instance selection instead of random permutation | ResNet image classification · MNIST test | accuracy: 98.67 -> 99.17 | Helped |
| Use AutoAssist instance selection instead of random permutation | ResNet image classification · FashionMNIST test | accuracy: 90.68 -> 90.99 | Helped |
| Use AutoAssist instance selection instead of random permutation | ResNet image classification · ExtendedMNIST test | accuracy: 87.21 -> 87.28 | Helped |
| Use AutoAssist instance selection instead of random permutation | ResNet image classification · CIFAR10 test | accuracy: 90.04 -> 90.23 | Helped |
| Use AutoAssist instance selection instead of random permutation | ResNet image classification · MNIST at 98.67% test accuracy | epochs: 24 -> 13.7 | Helped |
| Use AutoAssist with sequential batch generation and training | Transformer base · Multi30K | sentence-pairs/second: 617.3 -> 382.7 | Hurt |
| Run assistant and boss asynchronously on CPU/GPU (ablation) | AutoAssist · Multi30K | sentence-pairs/second: 382.7 -> 586.0 | Helped |
| Select training instances with AutoAssist rather than vanilla sampling | Transformer base · WMT14 En-De, BLEU reach 26 | tokens: 1.82×10^9 -> 1.18×10^9 | Helped |
| Select training instances with AutoAssist rather than vanilla sampling | Transformer base · WMT14 En-De, BLEU reach 27 | tokens: 3.22×10^9 -> 3.01×10^9 | Helped |
| Select training instances with AutoAssist rather than vanilla sampling | Transformer base · WMT14 En-De | BLEU: 27.1 -> 27.1 | No clear effect |
Closest papers by meaning
- Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks (ICLR 2018 · similarity 0.87)
- DeepOBS: A Deep Learning Optimizer Benchmark Suite (ICLR 2019 · similarity 0.87)
- AutoGO: Automated Computation Graph Optimization for Neural Network Evolution (NeurIPS 2023 · similarity 0.87)
- AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters (NeurIPS 2019 · similarity 0.86)
- Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch (CVPR 2024 · similarity 0.85)
- Auto-Compressing Networks (NeurIPS 2025 · similarity 0.85)
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.