{"total":35,"rows":[{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49,"area":null},{"id":"2106.02990","title":"Self-Damaging Contrastive Learning","created":"2021-06-06","cited_by_count":48,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2305.02190","title":"Rethinking Graph Lottery Tickets: Graph Sparsity Matters","created":"2023-05-03","cited_by_count":23,"area":null},{"id":"2105.06747","title":"Troubleshooting Blind Image Quality Models in the Wild","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2310.02277","title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","created":"2023-09-29","cited_by_count":13,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2107.02086","title":"One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget","created":"2021-07-05","cited_by_count":6,"area":null},{"id":"2202.01290","title":"Cyclical Pruning for Sparse Neural Networks","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2304.09527","title":"Single-View View Synthesis with Self-Rectified Pseudo-Stereo","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2306.11903","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2112.15445","title":"Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction","created":"2021-12-28","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2404.03687","title":"DRIVE: Dual Gradient-Based Rapid Iterative Pruning","created":"2024-04-01","cited_by_count":3,"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":"2303.15479","title":"Exploring the Performance of Pruning Methods in Neural Networks: An Empirical Study of the Lottery Ticket Hypothesis","created":"2023-03-26","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":"2204.01640","title":"APP: Anytime Progressive Pruning","created":"2022-04-04","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":"2308.07939","title":"Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2206.08175","title":"Not All Lotteries Are Made Equal","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2304.06840","title":"Structured Pruning for Multi-Task Deep Neural Networks","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2306.16557","title":"Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2311.03956","title":"Cup Curriculum: Curriculum Learning on Model Capacity","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2403.02429","title":"Towards efficient deep autoencoders for multivariate time series anomaly detection","created":"2024-03-04","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":"2609.10311","title":"One Loop, Two Gains: Can Active Learning win the Lottery for Free?","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}