Research map / Architectures and efficiency / Quantization
Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a topological-entropy-based metric for mixed-precision quantization policy search on neural networks, aiming for efficient and generalizable bit-width assignment.
Problem
Existing mixed-precision quantization (MPQ) methods produce quantization policies that struggle to generalize and are costly to obtain when assigning per-layer bit-widths for deep neural networks under resource constraints.
Approach
Uses topological entropy as the basis for assigning per-layer bit-widths, aiming for a search that is both efficient and transferable across settings; the abstract is truncated so the precise mechanism is not confirmed.
Closest papers by meaning
- InfoQ: Mixed-Precision Quantization via Global Information Flow (AAAI 2026 · similarity 0.91)
- HAWQ-V3: Dyadic Neural Network Quantization (ICML 2021 · similarity 0.89)
- Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning (ICML 2025 · similarity 0.88)
- ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization (NeurIPS 2025 · similarity 0.88)
- Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning (CVPR 2024 · similarity 0.87)
- PTMQ: Post-training Multi-Bit Quantization of Neural Networks (AAAI 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.