Research map / Architectures and efficiency / Pruning and efficient tuning
On the Existence of Universal Lottery Tickets
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 |
|---|---|---|---|
| Prune the proposed polynomial architecture from a randomly initialized mother network | Polynomial universal ticket · Polynomial function family | maximum approximation error: 0.001 | Helped |
| Increase the mother-network width from [1, 250, 21, 250, 1] to [1, 250, 250, 250, 1] (ablation) | Fourier universal ticket · Fourier basis, sin(2πx) on [0,1] | fraction of parameters remaining: 0.038 -> 0.0035 | Helped |
| Use edge-popup pruning on the polynomial architecture | Polynomial architecture · MNIST | accuracy: 92.4 ± 0.5 | Helped |
| Use edge-popup pruning on the Fourier architecture | Fourier architecture · MNIST | accuracy: 97.9 ± 0.1 | Helped |
Closest papers by meaning
- Convolutional and Residual Networks Provably Contain Lottery Tickets (ICML 2022 · similarity 0.94)
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (ICLR 2019 · similarity 0.93)
- Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks (ICLR 2022 · similarity 0.93)
- Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets (NeurIPS 2023 · similarity 0.92)
- On the Sparsity of the Strong Lottery Ticket Hypothesis (NeurIPS 2024 · similarity 0.90)
- Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win (ICML 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.
