Research map / Architectures and efficiency / Quantization
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
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 SDP-based sampling instead of backpropagation-based quantization | Binary quantized bilinear network · Planted synthetic dataset | training cost | Helped |
| Use SDP-based sampling instead of backpropagation-based quantization | Binary quantized bilinear network · Planted synthetic dataset test set | test cost | Helped |
| Use SDP-based sampling instead of post-training quantization after backpropagation | Binary quantized bilinear network · Breast cancer | classification accuracy | Helped |
| Use SDP-based sampling instead of backpropagation-based quantization | Binary quantized bilinear network · Breast cancer | time to return output | Helped |
| Use SDP-based sampling instead of backpropagation-based quantization | Binary quantized bilinear network · Ionosphere | classification accuracy | Helped |
| Increase the number of sampled neurons (ablation) | SDP-based sampling method · Planted synthetic dataset | training cost | Helped |
| Increase the number of neurons (ablation) | SDP-based sampling and backpropagation methods · Credit approval | classification accuracy | Helped |
| Use SDP-based sampling instead of quantized backpropagation | Binary quantized bilinear network · Credit approval | classification accuracy | Helped |
| Use SDP-based sampling instead of post-training-quantized ReLU network | Quantized network · Ionosphere | classification accuracy | Helped |
Closest papers by meaning
- Training Quantized Nets: A Deeper Understanding (NeurIPS 2017 · similarity 0.90)
- Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks (ICLR 2026 · similarity 0.88)
- The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions (ICLR 2022 · similarity 0.88)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 2024 · similarity 0.87)
- Convex Formulations for Training Two-Layer ReLU Neural Networks (ICLR 2025 · similarity 0.87)
- Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · similarity 0.86)
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.