mlsanityData to 7 Oct 2026

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

arXiv 2002.00585 ↗First posted 3 Feb 2020cs.LG stat.MLcited by 200

Not on the map. Why?

Abstract (arXiv)

The lottery ticket hypothesis (Frankle and Carbin, 2018), states that a randomly-initialized network contains a small subnetwork such that, when trained in isolation, can compete with the performance of the original network. We prove an even stronger hypothesis (as was also conjectured in Ramanujan et al., 2019), showing that for every bounded distribution and every target network with bounded weights, a sufficiently over-parameterized neural network with random weights contains a subnetwork with roughly the same accuracy as the target network, without any further training.

Key facts. Cited by 200 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 49; 2023: 37; 2024: 31; 2025: 30; 2026: 21.

200 papers.

Sort:

By area:

  1. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 641
  2. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  3. 2021Composable Sparse Fine-Tuning for Cross-Lingual Transfercited by 144
  4. 2021Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Modelscited by 75
  5. 2022Finding Skill Neurons in Pre-trained Transformer-based Language Modelscited by 65
  6. 2021Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Networkcited by 55
  7. 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 50
  8. 2021Playing Lottery Tickets with Vision and Languagecited by 45
  9. 2021Recent Advances on Neural Network Pruning at Initializationcited by 41
  10. 2022The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networkscited by 41
  11. 2022Rare Gems: Finding Lottery Tickets at Initializationcited by 34
  12. 2021MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworkscited by 32
38 more
  1. 2021GANs Can Play Lottery Tickets Toocited by 32
  2. 2021On the Existence of Universal Lottery Ticketscited by 30
  3. 2023Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammarscited by 30
  4. 2021Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networkscited by 29
  5. 2022Why Random Pruning Is All We Need to Start Sparsecited by 26
  6. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  7. 2022Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraintscited by 25
  8. 2023Proving Linear Mode Connectivity of Neural Networks via Optimal Transportcited by 24
  9. 2023Rethinking Graph Lottery Tickets: Graph Sparsity Matterscited by 23
  10. 2024A Survey of Lottery Ticket Hypothesiscited by 23
  11. 2021Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?cited by 22
  12. 2022Most Activation Functions Can Win the Lottery Without Excessive Depthcited by 21
  13. 2021Pruning Randomly Initialized Neural Networks with Iterative Randomizationcited by 20
  14. 2021Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsitycited by 20
  15. 2022A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesiscited by 19
  16. 2022DataMUX: Data Multiplexing for Neural Networkscited by 18
  17. 2022Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)cited by 18
  18. 2024How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teacherscited by 18
  19. 2022Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNscited by 16
  20. 2022Convolutional and Residual Networks Provably Contain Lottery Ticketscited by 16
  21. 2023Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networkscited by 16
  22. 2021A Probabilistic Approach to Neural Network Pruningcited by 15
  23. 2023Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modelingcited by 15
  24. 2024Masks, Signs, And Learning Rate Rewindingcited by 15
  25. 2021A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applicationscited by 14
  26. 2021Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networkscited by 14
  27. 2022Provable and Efficient Continual Representation Learningcited by 14
  28. 2022Generalization Properties of NAS under Activation and Skip Connection Searchcited by 14
  29. 2021Plant 'n' Seek: Can You Find the Winning Ticket?cited by 13
  30. 2022To update or not to update? Neurons at equilibrium in deep modelscited by 13
  31. 2022Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Surveycited by 12
  32. 2023Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalizationcited by 12
  33. 2024Mask in the Mirror: Implicit Sparsificationcited by 12
  34. 2023The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive fieldcited by 11
  35. 2023Successfully Applying Lottery Ticket Hypothesis to Diffusion Modelcited by 11
  36. 2022Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processingcited by 10
  37. 2021Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offsetcited by 9
  38. 2021Equal Bits: Enforcing Equally Distributed Binary Network Weightscited by 9

50 most cited of 200 All 200 (JSON)