{"list":"other","total":60,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1605.09522","title":"Kernel Mean Embedding of Distributions: A Review and Beyond","created":"2016-05-31","cited_by_count":364},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"1902.06015","title":"Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit","created":"2019-02-16","cited_by_count":187},{"id":"1905.04943","title":"Universal Invariant and Equivariant Graph Neural Networks","created":"2019-05-13","cited_by_count":183},{"id":"2105.09016","title":"E(n) Equivariant Normalizing Flows","created":"2021-05-19","cited_by_count":165},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"1605.00251","title":"A vector-contraction inequality for Rademacher complexities","created":"2016-05-01","cited_by_count":142},{"id":"1811.08888","title":"Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks","created":"2018-11-21","cited_by_count":141},{"id":"1810.00825","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","created":"2018-10-01","cited_by_count":132},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2006.10540","title":"Infinite attention: NNGP and NTK for deep attention networks","created":"2020-06-18","cited_by_count":121},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"1906.00232","title":"Kernel Instrumental Variable Regression","created":"2019-06-01","cited_by_count":118},{"id":"2106.02584","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","created":"2021-06-04","cited_by_count":113},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1808.09372","title":"Mean Field Analysis of Neural Networks: A Central Limit Theorem","created":"2018-08-28","cited_by_count":107},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1810.12065","title":"On the Convergence Rate of Training Recurrent Neural Networks","created":"2018-10-29","cited_by_count":82},{"id":"1305.5029","title":"Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates","created":"2013-05-22","cited_by_count":65},{"id":"2010.00977","title":"Group Equivariant Stand-Alone Self-Attention For Vision","created":"2020-10-02","cited_by_count":63},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2202.07230","title":"Geometrically Equivariant Graph Neural Networks: A Survey","created":"2022-02-15","cited_by_count":56},{"id":"1806.07808","title":"Learning One-hidden-layer ReLU Networks via Gradient Descent","created":"2018-06-20","cited_by_count":50},{"id":"2007.02876","title":"A Mathematical Theory of Attention","created":"2020-07-06","cited_by_count":46},{"id":"1802.06093","title":"Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks","created":"2018-02-16","cited_by_count":44},{"id":"1610.04574","title":"Generalization Error of Invariant Classifiers","created":"2016-10-14","cited_by_count":42},{"id":"2012.04115","title":"Generalization bounds for deep learning","created":"2020-12-07","cited_by_count":38},{"id":"1910.06552","title":"Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces","created":"2019-10-15","cited_by_count":34},{"id":"1902.02880","title":"Mean Field Limit of the Learning Dynamics of Multilayer Neural Networks","created":"2019-02-07","cited_by_count":25},{"id":"2111.05529","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","created":"2021-11-10","cited_by_count":22},{"id":"1804.05012","title":"Representing smooth functions as compositions of near-identity functions with implications for deep network optimization","created":"2018-04-13","cited_by_count":15},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12}],"next_cursor":null}