{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"2006.04884","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","created":"2020-06-08","cited_by_count":255},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243},{"id":"1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent","created":"2019-05-29","cited_by_count":217},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"1411.8003","title":"Guaranteed Matrix Completion via Non-convex Factorization","created":"2014-11-28","cited_by_count":82},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82},{"id":"2008.05441","title":"Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network","created":"2020-08-12","cited_by_count":74},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58},{"id":"1910.13923","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer","created":"2019-10-30","cited_by_count":47},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41},{"id":"1806.06950","title":"GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking","created":"2018-06-18","cited_by_count":32},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28},{"id":"1812.02402","title":"Trained Rank Pruning for Efficient Deep Neural Networks","created":"2018-12-06","cited_by_count":23},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","cited_by_count":20},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20},{"id":"2006.10598","title":"Neural Parameter Allocation Search","created":"2020-06-18","cited_by_count":15},{"id":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","cited_by_count":14},{"id":"2402.01052","title":"Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation","created":"2024-02-01","cited_by_count":14},{"id":"2410.02117","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","created":"2024-10-03","cited_by_count":13},{"id":"1404.5692","title":"Forward - Backward Greedy Algorithms for Atomic Norm Regularization","created":"2014-04-23","cited_by_count":9},{"id":"2006.13347","title":"Principal Component Networks: Parameter Reduction Early in Training","created":"2020-06-23","cited_by_count":9},{"id":"1410.0641","title":"An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions","created":"2014-10-02","cited_by_count":8},{"id":"2210.12497","title":"Deep Linear Networks for Matrix Completion -- An Infinite Depth Limit","created":"2022-10-22","cited_by_count":8},{"id":"2408.17163","title":"The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information","created":"2024-08-30","cited_by_count":8},{"id":"2411.08735","title":"New advances in universal approximation with neural networks of minimal width","created":"2024-11-13","cited_by_count":5},{"id":"1910.03935","title":"On geodesic triangles with right angles in a dually flat space","created":"2019-10-09","cited_by_count":4},{"id":"2401.08505","title":"Harnessing Orthogonality to Train Low-Rank Neural Networks","created":"2024-01-16","cited_by_count":4},{"id":"2407.04797","title":"Revealing the Utilized Rank of Subspaces of Learning in Neural Networks","created":"2024-07-05","cited_by_count":4},{"id":"2412.02328","title":"Efficient Model Compression Techniques with FishLeg","created":"2024-12-03","cited_by_count":4},{"id":"2411.09816","title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","created":"2024-11-14","cited_by_count":3},{"id":"2005.01995","title":"Adaptive Low-Rank Factorization to regularize shallow and deep neural networks","created":"2020-05-05","cited_by_count":2},{"id":"2112.14733","title":"On Asymptotic Linear Convergence Rate of Iterative Hard Thresholding for Matrix Completion","created":"2021-12-29","cited_by_count":1},{"id":"2301.05002","title":"Convergence Analysis of the Proximal Gradient Method in the Presence of the Kurdyka-{\\L}ojasiewicz Property without Global Lipschitz Assumptions","created":"2023-01-12","cited_by_count":1},{"id":"2310.12688","title":"Compression of Recurrent Neural Networks using Matrix Factorization","created":"2023-10-19","cited_by_count":1}],"next_cursor":null}