{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"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":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2402.14735","title":"How Transformers Learn Causal Structure with Gradient Descent","created":"2024-02-22","cited_by_count":118},{"id":"2310.05249","title":"In-Context Convergence of Transformers","created":"2023-10-08","cited_by_count":115},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"2006.08680","title":"Shape Matters: Understanding the Implicit Bias of the Noise Covariance","created":"2020-06-15","cited_by_count":88},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"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":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"2010.02501","title":"A Unifying View on Implicit Bias in Training Linear Neural Networks","created":"2020-10-06","cited_by_count":75},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74},{"id":"2402.19442","title":"Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality","created":"2024-02-29","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":"2102.09769","title":"On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent","created":"2021-02-19","cited_by_count":70},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57},{"id":"1905.07325","title":"Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models","created":"2019-05-17","cited_by_count":53},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37},{"id":"2302.08982","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability","created":"2023-02-17","cited_by_count":36},{"id":"2107.00595","title":"Fast Margin Maximization via Dual Acceleration","created":"2021-07-01","cited_by_count":33},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30},{"id":"1806.00952","title":"Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization","created":"2018-06-04","cited_by_count":29},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24},{"id":"2007.08322","title":"Understanding Implicit Regularization in Over-Parameterized Single Index Model","created":"2020-07-16","cited_by_count":12},{"id":"2302.00257","title":"Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression","created":"2023-02-01","cited_by_count":4},{"id":"2307.07410","title":"Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks","created":"2023-07-13","cited_by_count":4}],"next_cursor":null}