Research map / Architectures and efficiency / Pruning and efficient tuning
Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network
James Diffenderfer, Bhavya Kailkhura
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Add learned BatchNorm parameters to MPT-1/32 (ablation) | ResNet-18 MPT · CIFAR-10 | Top-1 accuracy: 94.66 -> 94.8 | Improved |
| Add learned BatchNorm parameters to MPT-1/1 (ablation) | VGG-Small MPT · CIFAR-10 | Top-1 accuracy: 88.52 -> 91.9 | Improved |
| Add learned BatchNorm parameters to MPT-1/32 (ablation) | WRN-50 MPT · ImageNet | Top-1 accuracy: 72.67 -> 74.03 | Improved |
| Add learned BatchNorm parameters to MPT-1/1 (ablation) | WRN-34 MPT · ImageNet | Top-1 accuracy: 45.06 -> 52.07 | Improved |
| Increase network depth (ablation) | MPT-1/32 and MPT-1/1 · CIFAR-10 | Top-1 accuracy | Improved |
| Increase network width (ablation) | MPT-1/32 and MPT-1/1 · CIFAR-10 | Top-1 accuracy | Improved |
| Increase pruning rate in narrower networks (ablation) | MPTs · CIFAR-10 | Top-1 accuracy | Hurt |
| Increase pruning rate in high-width networks (ablation) | MPTs · CIFAR-10 | Top-1 accuracy | No clear effect |
| Use binary weights and activations instead of binary weights with real-valued activations (ablation) | MPTs · CIFAR-10 depth experiments | Top-1 accuracy | Mixed |
Closest papers by meaning
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.92)
- Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks (NeurIPS 2021 · similarity 0.92)
- Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks (ICLR 2022 · similarity 0.91)
- Efficient Lottery Ticket Finding: Less Data is More (ICML 2021 · similarity 0.91)
- Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not? (ICML 2021 · similarity 0.91)
- Find A Winning Sign: Sign Is All We Need to Win the Lottery (ICLR 2025 · similarity 0.89)
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.
