{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"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":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"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":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1810.10531","title":"A mathematical theory of semantic development in deep neural networks","created":"2018-10-23","cited_by_count":186},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"id":"1704.00708","title":"No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis","created":"2017-04-03","cited_by_count":129},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93},{"id":"1602.06664","title":"A Geometric Analysis of Phase Retrieval","created":"2016-02-22","cited_by_count":92},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"1411.8003","title":"Guaranteed Matrix Completion via Non-convex Factorization","created":"2014-11-28","cited_by_count":82},{"id":"1605.07221","title":"Global Optimality of Local Search for Low Rank Matrix Recovery","created":"2016-05-23","cited_by_count":82},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74},{"id":"2007.06738","title":"Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy","created":"2020-07-13","cited_by_count":71},{"id":"1906.05392","title":"Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian","created":"2019-06-12","cited_by_count":67},{"id":"1909.12051","title":"The Implicit Bias of Depth: How Incremental Learning Drives Generalization","created":"2019-09-26","cited_by_count":64},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53},{"id":"1901.08572","title":"Width Provably Matters in Optimization for Deep Linear Neural Networks","created":"2019-01-24","cited_by_count":52},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50},{"id":"2012.05156","title":"Implicit Regularization in ReLU Networks with the Square Loss","created":"2020-12-09","cited_by_count":45},{"id":"2011.13772","title":"Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank","created":"2020-11-27","cited_by_count":42},{"id":"1605.07051","title":"Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent","created":"2016-05-23","cited_by_count":39},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36},{"id":"2311.02960","title":"Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination","created":"2023-11-06","cited_by_count":32},{"id":"2007.06753","title":"From Symmetry to Geometry: Tractable Nonconvex Problems","created":"2020-07-14","cited_by_count":29},{"id":"2006.08857","title":"Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization","created":"2020-06-16","cited_by_count":26},{"id":"2109.11154","title":"Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery","created":"2021-09-23","cited_by_count":22},{"id":"2402.13728","title":"Average gradient outer product as a mechanism for deep neural collapse","created":"2024-02-21","cited_by_count":22},{"id":"2305.17446","title":"Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models","created":"2023-05-27","cited_by_count":19},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14},{"id":"1810.11344","title":"Benefits of over-parameterization with EM","created":"2018-10-26","cited_by_count":10},{"id":"1901.03611","title":"The Benefits of Over-parameterization at Initialization in Deep ReLU Networks","created":"2019-01-11","cited_by_count":8}],"next_cursor":null}