{"total":25,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"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":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","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":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","cited_by_count":8,"area":null},{"id":"2203.02770","title":"Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance","created":"2022-03-05","cited_by_count":7,"area":null},{"id":"2101.12016","title":"Baseline Pruning-Based Approach to Trojan Detection in Neural Networks","created":"2021-01-22","cited_by_count":5,"area":null},{"id":"2101.02268","title":"LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification","created":"2021-01-06","cited_by_count":4,"area":null},{"id":"2308.00093","title":"Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification","created":"2023-07-28","cited_by_count":4,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2201.08417","title":"Scalable Sampling for Nonsymmetric Determinantal Point Processes","created":"2022-01-20","cited_by_count":2,"area":null},{"id":"2312.09821","title":"Fragility, Robustness and Antifragility in Deep Learning","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2204.04348","title":"Neuronal diversity can improve machine learning for physics and beyond","created":"2022-04-09","cited_by_count":0,"area":null},{"id":"2204.09134","title":"Diverse Imagenet Models Transfer Better","created":"2022-04-19","cited_by_count":0,"area":null},{"id":"2210.16504","title":"A pruning method based on the dissimilarity of angle among channels and filters","created":"2022-10-29","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":"2305.18417","title":"Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization","created":"2023-05-28","cited_by_count":0,"area":null},{"id":"2305.18448","title":"Neural Network Reduction with Guided Regularizers","created":"2023-05-29","cited_by_count":0,"area":null}],"next_cursor":null}