Research map / Architectures and efficiency / Pruning and efficient tuning
Pruning at initialization
Prunes before training using data-free scores and examines when sparse initializations suffice.
24 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2024) · an approach in Pruning and efficient tuning, keyword cluster “lottery · tickets · winning”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
5 papers in 2023–24 and 0 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.8% to 0.0%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2019 · Rethinking the Value of Network Pruning (ICLR 2019 · 958 citations)
- 2020 · Picking Winning Tickets Before Training by Preserving Gradient Flow (ICLR 2020 · 138 citations)
- 2021 · Sparse Training via Boosting Pruning Plasticity with Neuroregeneration (NeurIPS 2021 · 13 citations)
- 2022 · How Well Do Sparse ImageNet Models Transfer? (CVPR 2022 · 22 citations)
- 2023 · Why Random Pruning Is All We Need to Start Sparse (ICML 2023 · 4 citations)
- 2024 · Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning (CVPR 2024 · 9 citations)
Earliest papers here
- Rethinking the Value of Network Pruning (ICLR 2019 · 958 citations)
- Picking Winning Tickets Before Training by Preserving Gradient Flow (ICLR 2020 · 138 citations)
- Pruning neural networks without any data by iteratively conserving synaptic flow (NeurIPS 2020 · 74 citations)
What has been tried
22 papers here report 235 measured changes (a component added, removed or swapped, compared with a baseline): helped 60%, no clear effect 12%, hurt 22%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| increase PX pruning rounds from T=1 to T=2 | CIFAR-10 at 98.20% sparsity · accuracy | 76.15 -> 76.47 | Helped | Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning (CVPR 2024 · 9 citations) |
| Increase the learning rate | Student-teacher task · rate of increase in correlation with label noise | Helped | No Free Prune: Information-Theoretic Barriers to Pruning at Initialization (ICML 2024 · 2 citations) | |
| add SWA trajectory averaging | CIFAR-10, 50% and 95% sparsity · accuracy | 94.43 ± 0.10 -> 94.74 ± 0.04; 93.73 ± 0.32 -> 94.23 ± 0.11 | Helped | Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning (ICLR 2024 · 0 citations) |
| Rewind batch-normalization parameters after each pruning iteration | CIFAR10, CIFAR100 · accuracy | Helped | Masks, Signs, And Learning Rate Rewinding (ICLR 2024) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 5 papers; from OpenAlex and the papers' affiliations).
- Helmholtz Center CISPA for Information Security · 2 papers
- CISPA Helmholtz Center for Information Security · 2 papers
Use it
Download BibTeX of 21 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Lottery ticket discovery (42 papers)
Elsewhere in the topic
- Low-rank compression and merging (226 papers)
- Structured network pruning (162 papers)
- Adapter-based parameter-efficient tuning (149 papers)
- LoRA variants and theory (121 papers)
- Parameter-efficient transfer analysis (97 papers)
- Sparse training from scratch (95 papers)
- Layer-wise pruning of LLMs (91 papers)
- Joint pruning and quantization (78 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).