{"total":81,"rows":[{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62,"area":null},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2106.00134","title":"GANs Can Play Lottery Tickets Too","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"area":null},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2106.09269","title":"Pruning Randomly Initialized Neural Networks with Iterative Randomization","created":"2021-06-17","cited_by_count":20,"area":null},{"id":"2206.04270","title":"A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2411.09702","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","created":"2024-11-14","cited_by_count":17,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2105.10065","title":"A Probabilistic Approach to Neural Network Pruning","created":"2021-05-20","cited_by_count":15,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2408.09966","title":"Mask in the Mirror: Implicit Sparsification","created":"2024-08-19","cited_by_count":14,"area":null},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2112.04002","title":"SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2203.14328","title":"On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks","created":"2022-03-27","cited_by_count":9,"area":null},{"id":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","cited_by_count":8,"area":null},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2101.06475","title":"Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks","created":"2021-01-16","cited_by_count":5,"area":null},{"id":"2201.12826","title":"OptG: Optimizing Gradient-driven Criteria in Network Sparsity","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2301.11936","title":"Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2110.08996","title":"Finding Everything within Random Binary Networks","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2110.11150","title":"Lottery Tickets with Nonzero Biases","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2205.15619","title":"Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2408.03220","title":"Masked Random Noise for Communication Efficient Federated Learning","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2210.16169","title":"LOFT: Finding Lottery Tickets through Filter-wise Training","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2210.16589","title":"Strong Lottery Ticket Hypothesis with $\\varepsilon$--perturbation","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2303.15953","title":"Randomly Initialized Subnetworks with Iterative Weight Recycling","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2305.12148","title":"Probabilistic Modeling: Proving the Lottery Ticket Hypothesis in Spiking Neural Network","created":"2023-05-20","cited_by_count":3,"area":null},{"id":"2311.09858","title":"Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2406.01755","title":"Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2410.14754","title":"On the Sparsity of the Strong Lottery Ticket Hypothesis","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2202.12986","title":"Extracting Effective Subnetworks with Gumbel-Softmax","created":"2022-02-25","cited_by_count":2,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2305.03395","title":"Sparsifying Bayesian neural networks with latent binary variables and normalizing flows","created":"2023-05-05","cited_by_count":2,"area":null},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2306.12190","title":"Quantifying lottery tickets under label noise: accuracy, calibration, and complexity","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2312.03236","title":"Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2510.00504","title":"A universal compression theory for lottery ticket hypothesis and neural scaling laws","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.08513","title":"SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.17515","title":"The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.04217","title":"The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2112.04905","title":"i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2302.05984","title":"Quantum Neuron Selection: Finding High Performing Subnetworks With Quantum Algorithms","created":"2023-02-12","cited_by_count":1,"area":null},{"id":"2302.11244","title":"Considering Layerwise Importance in the Lottery Ticket Hypothesis","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2403.04805","title":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2406.02773","title":"Cyclic Sparse Training: Is it Enough?","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2504.17520","title":"Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2508.11020","title":"Quantization vs Pruning: Insights from the Strong Lottery Ticket Hypothesis","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2303.10408","title":"ExplainFix: Explainable Spatially Fixed Deep Networks","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2309.10834","title":"Communication-Efficient Federated Learning via Regularized Sparse Random Networks","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2404.10997","title":"Online Algorithms with Limited Data Retention","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2407.18625","title":"Topology Optimization of Random Memristors for Input-Aware Dynamic SNN","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2503.14246","title":"Trading-off Accuracy and Communication Cost in Federated Learning","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2508.08877","title":"Towards Scalable Lottery Ticket Networks using Genetic Algorithms","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2603.02234","title":"Structured vs. Unstructured Pruning: An Exponential Gap","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.08914","title":"Uncovering a Winning Lottery Ticket with Continuously Relaxed Bernoulli Gates","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.16470","title":"Strategic Over-Parameterization for Generalizable Low-Rank Adaptation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.03860","title":"A Unified Framework for Quantized and Continuous Strong Lottery Tickets","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.20555","title":"Double-Scoring: Reliable Extraction of Strong Lottery Tickets","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.24401","title":"Artificial Structure Function Search: Preserving Artificial Functional Connectivity for Structured Pruning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32615","title":"Stabilizing the Dynamic Low-Rank Training","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}