{"total":99,"rows":[{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"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":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2107.00166","title":"Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?","created":"2021-07-01","cited_by_count":52,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2110.14678","title":"Meta-Learning Sparse Implicit Neural Representations","created":"2021-10-27","cited_by_count":48,"area":null},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"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":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2106.00134","title":"GANs Can Play Lottery Tickets Too","created":"2021-05-31","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":"2210.04457","title":"XPrompt: Exploring the Extreme of Prompt Tuning","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2205.12672","title":"Discovering Language-neutral Sub-networks in Multilingual Language Models","created":"2022-05-25","cited_by_count":28,"area":null},{"id":"2207.01382","title":"Exploring Lottery Ticket Hypothesis in Spiking Neural Networks","created":"2022-07-04","cited_by_count":26,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2105.01648","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","created":"2021-05-04","cited_by_count":24,"area":null},{"id":"2310.08670","title":"Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction","created":"2023-10-12","cited_by_count":24,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2404.04612","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","created":"2024-04-06","cited_by_count":24,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2305.02190","title":"Rethinking Graph Lottery Tickets: Graph Sparsity Matters","created":"2023-05-03","cited_by_count":23,"area":null},{"id":"2102.11068","title":"Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?","created":"2021-02-19","cited_by_count":22,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"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":"2206.01342","title":"Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2103.05152","title":"Knowledge Evolution in Neural Networks","created":"2021-03-09","cited_by_count":18,"area":null},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2202.02664","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","created":"2022-02-06","cited_by_count":15,"area":null},{"id":"2308.10438","title":"Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks","created":"2023-08-21","cited_by_count":15,"area":null},{"id":"2108.03214","title":"Simple Modifications to Improve Tabular Neural Networks","created":"2021-08-06","cited_by_count":14,"area":null},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","cited_by_count":13,"area":null},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","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":"2310.16391","title":"Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2106.06955","title":"Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win","created":"2021-06-13","cited_by_count":11,"area":null},{"id":"2208.10842","title":"Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost","created":"2022-08-23","cited_by_count":11,"area":null},{"id":"2411.02824","title":"Layer-Adaptive State Pruning for Deep State Space Models","created":"2024-11-05","cited_by_count":10,"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":"2110.03210","title":"Universality of Winning Tickets: A Renormalization Group Perspective","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2202.12400","title":"The rise of the lottery heroes: why zero-shot pruning is hard","created":"2022-02-24","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":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2101.04073","title":"Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization","created":"2021-01-11","cited_by_count":4,"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":"2201.11803","title":"On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning","created":"2022-01-27","cited_by_count":4,"area":null},{"id":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2104.13343","title":"Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?","created":"2021-04-27","cited_by_count":3,"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":"2212.12770","title":"COLT: Cyclic Overlapping Lottery Tickets for Faster Pruning of Convolutional Neural Networks","created":"2022-12-24","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":"2308.14969","title":"Uncovering the Hidden Cost of Model Compression","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2408.14601","title":"3D Point Cloud Network Pruning: When Some Weights Do not Matter","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2103.16889","title":"Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2112.08227","title":"An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2206.06563","title":"Zeroth-Order Topological Insights into Iterative Magnitude Pruning","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2209.05683","title":"One-shot Network Pruning at Initialization with Discriminative Image Patches","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2304.13164","title":"Towards Compute-Optimal Transfer Learning","created":"2023-04-25","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":"2306.00045","title":"Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2408.03913","title":"AdapMTL: Adaptive Pruning Framework for Multitask Learning Model","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2602.00446","title":"Towards Building Non-Fine-Tunable Foundation Models","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.18960","title":"Modularity is the Bedrock of Natural and Artificial Intelligence","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2207.04227","title":"On the Robustness and Anomaly Detection of Sparse Neural Networks","created":"2022-07-09","cited_by_count":1,"area":null},{"id":"2211.13935","title":"LU decomposition and Toeplitz decomposition of a neural network","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2212.03659","title":"Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks","created":"2022-12-07","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":"2308.03128","title":"Iterative Magnitude Pruning as a Renormalisation Group: A Study in The Context of The Lottery Ticket Hypothesis","created":"2023-08-06","cited_by_count":1,"area":null},{"id":"2405.09037","title":"SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning","created":"2024-05-15","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":"2407.20281","title":"NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2412.06545","title":"On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2501.15592","title":"Information Consistent Pruning: How to Efficiently Search for Sparse Networks?","created":"2025-01-26","cited_by_count":1,"area":null},{"id":"2503.22451","title":"STADE: Standard Deviation as a Pruning Metric","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2510.07227","title":"Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2602.00534","title":"AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.04832","title":"It's Not a Lottery, It's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2107.03690","title":"Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2109.03862","title":"Juvenile state hypothesis: What we can learn from lottery ticket hypothesis researches?","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2202.11484","title":"Reconstruction Task Finds Universal Winning Tickets","created":"2022-02-23","cited_by_count":0,"area":null},{"id":"2209.13378","title":"Neural Network Panning: Screening the Optimal Sparse Network Before Training","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2306.02415","title":"Biologically-Motivated Learning Model for Instructed Visual Processing","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2306.09863","title":"Transferability of Winning Lottery Tickets in Neural Network Differential Equation Solvers","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2312.03889","title":"A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2402.10339","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2408.14757","title":"Learning effective pruning at initialization from iterative pruning","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2410.24187","title":"Chasing Better Deep Image Priors between Over- and Under-parameterization","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2504.18785","title":"ALF: Advertiser Large Foundation Model for Multi-Modal Advertiser Understanding","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2506.07587","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2510.18636","title":"C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.06265","title":"CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2606.12278","title":"Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.27031","title":"Lottery Tickets Are Not Deployment Tickets","created":"2026-07-29","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}