Research map / Architectures and efficiency / Pruning and efficient tuning
Dual Lottery Ticket Hypothesis
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 |
|---|---|---|---|
| transform a uniformly random sparse ticket with RST rather than train it directly from scratch | ResNet56 · CIFAR10 and CIFAR100, 50%–98% sparsity | top-1 accuracy | Helped |
| transform a uniformly random sparse ticket with RST rather than use LTH Iter-5 | ResNet56 · CIFAR10, 50%–98% sparsity | top-1 accuracy | Mixed |
| transform a uniformly random sparse ticket with RST rather than use LTH Iter-5 | ResNet56 · CIFAR100, 50%–98% sparsity | top-1 accuracy | Helped |
| use RST rather than LTH | ResNet18 · ImageNet Subset, 50% and 70% sparsity | top-1 accuracy: 77.87 -> 78.24; 76.48 -> 76.80 | Helped |
| use RST rather than GraSP | ResNet56 · CIFAR10 and CIFAR100, 50%–98% sparsity | top-1 accuracy | Helped |
| use RST rather than GraSP | ResNet18 · ImageNet Subset, 70%–95% sparsity | Acc@1 | Helped |
| add iterative transformation cycles instead of using one-shot RST (ablation) | RST · CIFAR10 and CIFAR100, most reported sparsities | top-1 accuracy | Helped |
| vary the number of RST cycles from 1 to 5 (ablation) | RST · CIFAR10 and CIFAR100, 50%–98% sparsity | top-1 accuracy | No clear effect |
| increase RST cycles from 1 to 5 (ablation) | RST · CIFAR10, 70% sparsity | top-1 accuracy: 92.50 -> 92.67 | Mixed |
| use random-ticket transformation rather than scratch training | RST · CIFAR10 and CIFAR100 | top-1 accuracy | Helped |
Closest papers by meaning
- The Elastic Lottery Ticket Hypothesis (NeurIPS 2021 · similarity 0.94)
- Find A Winning Sign: Sign Is All We Need to Win the Lottery (ICLR 2025 · similarity 0.93)
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.93)
- Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks (NeurIPS 2021 · similarity 0.92)
- On the Sparsity of the Strong Lottery Ticket Hypothesis (NeurIPS 2024 · similarity 0.91)
- Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win (ICML 2025 · similarity 0.91)
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.