{"list":"other","total":84,"rows":[{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"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":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1704.04289","title":"Stochastic Gradient Descent as Approximate Bayesian Inference","created":"2017-04-13","cited_by_count":300},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"1802.08760","title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","created":"2018-02-23","cited_by_count":189},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"1906.00904","title":"Deep ReLU Networks Have Surprisingly Few Activation Patterns","created":"2019-06-03","cited_by_count":161},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"1511.06251","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","created":"2015-11-19","cited_by_count":142},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"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":"1811.01558","title":"Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations","created":"2018-11-05","cited_by_count":114},{"id":"1810.00113","title":"Predicting the Generalization Gap in Deep Networks with Margin Distributions","created":"2018-09-28","cited_by_count":113},{"id":"1803.01719","title":"How to Start Training: The Effect of Initialization and Architecture","created":"2018-03-05","cited_by_count":109},{"id":"2205.09653","title":"Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks","created":"2022-05-19","cited_by_count":105},{"id":"1801.03744","title":"Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?","created":"2018-01-11","cited_by_count":94},{"id":"2402.09963","title":"Why are Sensitive Functions Hard for Transformers?","created":"2024-02-15","cited_by_count":74},{"id":"2211.12316","title":"Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions","created":"2022-11-22","cited_by_count":70},{"id":"1812.03981","title":"Theoretical Analysis of Auto Rate-Tuning by Batch Normalization","created":"2018-12-10","cited_by_count":65},{"id":"2010.02916","title":"Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate","created":"2020-10-06","cited_by_count":59},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50},{"id":"1806.05394","title":"Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks","created":"2018-06-14","cited_by_count":45},{"id":"2304.03408","title":"Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks","created":"2023-04-06","cited_by_count":43},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33},{"id":"2304.06670","title":"Deep neural networks have an inbuilt Occam's razor","created":"2023-04-13","cited_by_count":28},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25},{"id":"1909.11522","title":"Neural networks are a priori biased towards Boolean functions with low entropy","created":"2019-09-25","cited_by_count":24},{"id":"2502.02531","title":"Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer","created":"2025-02-04","cited_by_count":19},{"id":"1902.00635","title":"Uniform-in-Time Weak Error Analysis for Stochastic Gradient Descent Algorithms via Diffusion Approximation","created":"2019-02-02","cited_by_count":15},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14},{"id":"2210.15898","title":"Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis","created":"2022-10-28","cited_by_count":13},{"id":"2502.07998","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","created":"2025-02-11","cited_by_count":13},{"id":"2007.01038","title":"Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?","created":"2020-07-02","cited_by_count":12},{"id":"2302.01952","title":"On a continuous time model of gradient descent dynamics and instability in deep learning","created":"2023-02-03","cited_by_count":11},{"id":"2312.16143","title":"On the Trajectories of SGD Without Replacement","created":"2023-12-26","cited_by_count":11},{"id":"2410.02348","title":"Simplicity bias and optimization threshold in two-layer ReLU networks","created":"2024-10-03","cited_by_count":11},{"id":"2509.26404","title":"SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From","created":"2025-09-30","cited_by_count":10},{"id":"2406.11110","title":"How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD","created":"2024-06-17","cited_by_count":8},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6},{"id":"2602.05927","title":"Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences","created":"2026-02-05","cited_by_count":6},{"id":"2309.02082","title":"Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent","created":"2023-09-05","cited_by_count":5},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4},{"id":"2509.26643","title":"Convergence and Divergence of Language Models under Different Random Seeds","created":"2025-09-30","cited_by_count":3},{"id":"2402.02454","title":"On the Role of Initialization on the Implicit Bias in Deep Linear Networks","created":"2024-02-04","cited_by_count":2},{"id":"2501.09137","title":"Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks","created":"2025-01-15","cited_by_count":2},{"id":"2509.08483","title":"Modified Loss of Momentum Gradient Descent: Fine-Grained Analysis","created":"2025-09-10","cited_by_count":2}],"next_cursor":null}