Research map / Architectures and efficiency / Quantization
Don’t Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
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 quantization with non-uniform Weibull-based quantization points (TinyScript) | activations and gradients · Cifar10 ResNet50 and ImageNet ResNet50 training | best error | Mixed |
| non-uniform Weibull quantization at n=4 vs uniform at n=8 (ablation) | gradients of a conv layer, WRN34 Cifar10 · Cifar10 WRN34 quantization variance | ||g~-g||^2/||g||^2 quantization variance | Helped |
| Weibull (non-uniform) quantization with n=4 on ImageNet ResNet50 | activations and gradients · ImageNet ResNet50 | validation error | Helped |
Closest papers by meaning
- Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction (ICML 2023 · similarity 0.90)
- Quantization Networks (CVPR 2019 · similarity 0.90)
- Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization (CVPR 2023 · similarity 0.89)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · similarity 0.89)
- Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators (ICLR 2024 · similarity 0.88)
- Quantization without Tears (CVPR 2025 · similarity 0.88)
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.