Research map / Architectures and efficiency / Pruning and efficient tuning
Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
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 |
|---|---|---|---|
| Interpolate IMP subnetworks greedily, selecting coefficients using held-out accuracy | Lottery Tickets · CIFAR-100 | accuracy: 1.88% | Helped |
| Interpolate IMP subnetworks greedily, selecting coefficients using held-out accuracy | Lottery Tickets · CIFAR-100 | accuracy: 1.72% | Helped |
| Interpolate IMP subnetworks | Lottery Tickets · ImageNet | accuracy: 0.55% | Helped |
| Interpolate IMP subnetworks | Lottery Tickets · CIFAR-100-C | accuracy: 2.36% | Helped |
| Add Lottery Pools interpolation to the pretrained dense model | Pretrained ResNet-18 · CIFAR-100 | accuracy: 2.22% | Helped |
| Replace searched interpolation coefficients with fixed averaging at α=0.5 (ablation) | Lottery Pools · CIFAR-10/100 | accuracy | Hurt |
| Use coefficient count 1 (α=0.5) rather than a larger coefficient search (ablation) | Lottery Pools · CIFAR-10/100 | accuracy | Hurt |
| Increase candidate coefficients from 3 to 7 (ablation) | Lottery Pools · CIFAR-10/100 | accuracy | Helped |
| Increase candidate tickets considered from 25% or 50% to all available IMP tickets (ablation) | Lottery Pools · CIFAR-10/100 | accuracy | Helped |
| Prune after completing greedy interpolation instead of pruning during each interpolation (ablation) | Lottery Pools · High sparsity levels | accuracy | Hurt |
| Use weight averaging without rewinding (ablation) | Lottery Tickets · CIFAR-100 | accuracy | Hurt |
| Average nearby IMP subnetworks rather than keep the original ticket (ablation) | Rewound Lottery Tickets · CIFAR-100 | accuracy | Helped |
Closest papers by meaning
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.91)
- The Elastic Lottery Ticket Hypothesis (NeurIPS 2021 · similarity 0.91)
- Dual Lottery Ticket Hypothesis (ICLR 2022 · similarity 0.91)
- Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets (ICML 2022 · similarity 0.91)
- On the Sparsity of the Strong Lottery Ticket Hypothesis (NeurIPS 2024 · similarity 0.89)
- Find A Winning Sign: Sign Is All We Need to Win the Lottery (ICLR 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.