{"total":62,"rows":[{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38,"area":null},{"id":"2207.06646","title":"DropNet: Reducing Neural Network Complexity via Iterative Pruning","created":"2022-07-14","cited_by_count":29,"area":null},{"id":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2105.13011","title":"Neural Network Training Using $\\ell_1$-Regularization and Bi-fidelity Data","created":"2021-05-27","cited_by_count":16,"area":null},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2108.11000","title":"Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details","created":"2021-08-25","cited_by_count":14,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2101.10181","title":"Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey","created":"2021-01-25","cited_by_count":9,"area":null},{"id":"2104.08829","title":"Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2107.14444","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2209.14881","title":"Sequential Attention for Feature Selection","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2212.05427","title":"Statistical guarantees for sparse deep learning","created":"2022-12-11","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2102.00160","title":"Deep Model Compression based on the Training History","created":"2021-01-30","cited_by_count":7,"area":null},{"id":"2106.02260","title":"Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2201.06776","title":"Pruning-aware Sparse Regularization for Network Pruning","created":"2022-01-18","cited_by_count":5,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2306.05056","title":"Magnitude Attention-based Dynamic Pruning","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2102.00390","title":"AACP: Model Compression by Accurate and Automatic Channel Pruning","created":"2021-01-31","cited_by_count":4,"area":null},{"id":"2308.09104","title":"Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2105.01064","title":"Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2106.15797","title":"Content-Aware Convolutional Neural Networks","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2208.06660","title":"Entropy Induced Pruning Framework for Convolutional Neural Networks","created":"2022-08-13","cited_by_count":3,"area":null},{"id":"2209.04448","title":"Learning sparse auto-encoders for green AI image coding","created":"2022-09-09","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":"2404.03687","title":"DRIVE: Dual Gradient-Based Rapid Iterative Pruning","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2202.03770","title":"Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning","created":"2022-02-08","cited_by_count":2,"area":null},{"id":"2207.02699","title":"Scaling Private Deep Learning with Low-Rank and Sparse Gradients","created":"2022-07-06","cited_by_count":2,"area":null},{"id":"2211.05525","title":"MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2504.09405","title":"Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2103.05804","title":"Reframing Neural Networks: Deep Structure in Overcomplete Representations","created":"2021-03-10","cited_by_count":1,"area":null},{"id":"2105.02085","title":"Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2107.07160","title":"Lockout: Sparse Regularization of Neural Networks","created":"2021-07-15","cited_by_count":1,"area":null},{"id":"2109.13061","title":"Searching for Minimal Optimal Neural Networks","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2202.12417","title":"Optimal channel selection with discrete QCQP","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2306.13410","title":"Explainable Lifelong Stream Learning Based on \"Glocal\" Pairwise Fusion","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2307.00684","title":"A Proximal Algorithm for Network Slimming","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2311.17943","title":"LayerCollapse: Adaptive compression of neural networks","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2408.02801","title":"Sparse Deep Learning Models with the $\\ell_1$ Regularization","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2501.13439","title":"One-Cycle Structured Pruning via Stability-Driven Subnetwork Search","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2510.12666","title":"Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2106.02914","title":"Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2110.05954","title":"Mining the Weights Knowledge for Optimizing Neural Network Structures","created":"2021-10-11","cited_by_count":0,"area":null},{"id":"2112.01675","title":"Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2210.09956","title":"Double Attention-based Lightweight Network for Plant Pest Recognition","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2211.08339","title":"Pruning Very Deep Neural Network Channels for Efficient Inference","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2307.07405","title":"Performance of $\\ell_1$ Regularization for Sparse Convex Optimization","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2405.02086","title":"Multi-level projection with exponential parallel speedup; Application to sparse auto-encoders neural networks","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2405.17506","title":"Subspace Node Pruning","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2407.16293","title":"A new Linear Time Bi-level $\\ell_{1,\\infty}$ projection ; Application to the sparsification of auto-encoders neural networks","created":"2024-07-23","cited_by_count":0,"area":null}],"next_cursor":null}