{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"1911.02727","title":"Understanding Knowledge Distillation in Non-autoregressive Machine Translation","created":"2019-11-07","cited_by_count":122},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"1908.05620","title":"Visualizing and Understanding the Effectiveness of BERT","created":"2019-08-15","cited_by_count":67},{"id":"2002.11794","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","created":"2020-02-26","cited_by_count":67},{"id":"2010.15581","title":"The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research","created":"2020-10-22","cited_by_count":67},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"1906.00532","title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","created":"2019-06-03","cited_by_count":59},{"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},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39},{"id":"2109.03228","title":"Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression","created":"2021-09-07","cited_by_count":38},{"id":"2103.06002","title":"Robustness to Pruning Predicts Generalization in Deep Neural Networks","created":"2021-03-10","cited_by_count":10}],"next_cursor":null}