{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"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":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"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":"1908.07086","title":"Human uncertainty makes classification more robust","created":"2019-08-19","cited_by_count":235},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"2312.10794","title":"A mathematical perspective on Transformers","created":"2023-12-17","cited_by_count":164},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","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":"2005.08054","title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","created":"2020-05-16","cited_by_count":97},{"id":"1806.09471","title":"Does data interpolation contradict statistical optimality?","created":"2018-06-25","cited_by_count":95},{"id":"1803.07300","title":"Risk and parameter convergence of logistic regression","created":"2018-03-20","cited_by_count":85},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"1803.06964","title":"A modern maximum-likelihood theory for high-dimensional logistic regression","created":"2018-03-19","cited_by_count":81},{"id":"1911.05822","title":"A Model of Double Descent for High-dimensional Binary Linear Classification","created":"2019-11-13","cited_by_count":81},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67},{"id":"1806.01796","title":"Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate","created":"2018-06-05","cited_by_count":64},{"id":"2002.11544","title":"The role of regularization in classification of high-dimensional noisy Gaussian mixture","created":"2020-02-26","cited_by_count":63},{"id":"2006.11226","title":"Gradient descent follows the regularization path for general losses","created":"2020-06-19","cited_by_count":59},{"id":"2106.09276","title":"Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting","created":"2021-06-17","cited_by_count":54},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52},{"id":"2010.11213","title":"Precise Statistical Analysis of Classification Accuracies for Adversarial Training","created":"2020-10-21","cited_by_count":50},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50},{"id":"2104.13628","title":"Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures","created":"2021-04-28","cited_by_count":49},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47},{"id":"1804.09753","title":"The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression","created":"2018-04-25","cited_by_count":46},{"id":"2207.00810","title":"Eliciting and Learning with Soft Labels from Every Annotator","created":"2022-07-02","cited_by_count":43},{"id":"1906.03830","title":"Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization","created":"2019-06-10","cited_by_count":40},{"id":"2010.09697","title":"Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent","created":"2020-10-19","cited_by_count":40},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40},{"id":"2201.11489","title":"The Implicit Bias of Benign Overfitting","created":"2022-01-27","cited_by_count":38},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37},{"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":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27},{"id":"2205.12808","title":"Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently","created":"2022-05-25","cited_by_count":26},{"id":"2006.05942","title":"On Uniform Convergence and Low-Norm Interpolation Learning","created":"2020-06-10","cited_by_count":24},{"id":"2203.03597","title":"Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias","created":"2022-03-07","cited_by_count":22},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21},{"id":"2203.12094","title":"Learning curves for the multi-class teacher-student perceptron","created":"2022-03-22","cited_by_count":17},{"id":"2012.02409","title":"When does gradient descent with logistic loss find interpolating two-layer networks?","created":"2020-12-04","cited_by_count":12},{"id":"2112.15250","title":"Benign Overfitting in Adversarially Robust Linear Classification","created":"2021-12-31","cited_by_count":11},{"id":"2305.17825","title":"Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions","created":"2023-05-28","cited_by_count":3},{"id":"2306.13255","title":"Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models","created":"2023-06-23","cited_by_count":3},{"id":"2402.08676","title":"A Convergence Analysis of Approximate Message Passing with Non-Separable Functions and Applications to Multi-Class Classification","created":"2024-02-13","cited_by_count":1}],"next_cursor":null}