{"list":"other","total":73,"rows":[{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"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":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"1901.06053","title":"A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks","created":"2019-01-18","cited_by_count":214},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2207.08799","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","created":"2022-07-18","cited_by_count":187},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"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":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"1511.06251","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","created":"2015-11-19","cited_by_count":142},{"id":"2202.08658","title":"The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks","created":"2022-02-17","cited_by_count":142},{"id":"1910.09336","title":"The Lean mathematical library","created":"2019-10-21","cited_by_count":134},{"id":"1712.07897","title":"Non-convex Optimization for Machine Learning","created":"2017-12-21","cited_by_count":133},{"id":"1712.08968","title":"Spurious Local Minima are Common in Two-Layer ReLU Neural Networks","created":"2017-12-24","cited_by_count":104},{"id":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"1709.01662","title":"Unsupervised Generative Modeling Using Matrix Product States","created":"2017-09-06","cited_by_count":88},{"id":"2106.15933","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","created":"2021-06-30","cited_by_count":85},{"id":"1703.07950","title":"Failures of Gradient-Based Deep Learning","created":"2017-03-23","cited_by_count":80},{"id":"1705.10412","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","created":"2017-05-29","cited_by_count":74},{"id":"1803.05999","title":"Escaping Saddles with Stochastic Gradients","created":"2018-03-15","cited_by_count":66},{"id":"1901.02217","title":"Tree Tensor Networks for Generative Modeling","created":"2019-01-08","cited_by_count":64},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62},{"id":"1910.05505","title":"Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers","created":"2019-10-12","cited_by_count":61},{"id":"2006.12011","title":"Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent","created":"2020-06-22","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":"1801.00315","title":"Learning Relevant Features of Data with Multi-scale Tensor Networks","created":"2017-12-31","cited_by_count":51},{"id":"1901.07417","title":"On Connected Sublevel Sets in Deep Learning","created":"2019-01-22","cited_by_count":51},{"id":"2307.00144","title":"Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows","created":"2023-06-30","cited_by_count":45},{"id":"1906.09069","title":"First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise","created":"2019-06-21","cited_by_count":44},{"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":"1512.09170","title":"Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization","created":"2015-12-30","cited_by_count":41},{"id":"1809.10749","title":"On the loss landscape of a class of deep neural networks with no bad local valleys","created":"2018-09-27","cited_by_count":38},{"id":"1910.01671","title":"Pure and Spurious Critical Points: a Geometric Study of Linear Networks","created":"2019-10-03","cited_by_count":33},{"id":"1707.02444","title":"Global optimality conditions for deep neural networks","created":"2017-07-08","cited_by_count":31},{"id":"1702.08580","title":"Depth Creates No Bad Local Minima","created":"2017-02-27","cited_by_count":29},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29},{"id":"2108.04190","title":"On the Power of Differentiable Learning versus PAC and SQ Learning","created":"2021-08-09","cited_by_count":28},{"id":"2410.08417","title":"Bilinear MLPs enable weight-based mechanistic interpretability","created":"2024-10-10","cited_by_count":28},{"id":"1609.01037","title":"Distribution-Specific Hardness of Learning Neural Networks","created":"2016-09-05","cited_by_count":27},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24},{"id":"1602.05908","title":"Efficient approaches for escaping higher order saddle points in non-convex optimization","created":"2016-02-18","cited_by_count":23},{"id":"1802.06384","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes","created":"2018-02-18","cited_by_count":21},{"id":"1810.07716","title":"The loss surface of deep linear networks viewed through the algebraic geometry lens","created":"2018-10-17","cited_by_count":20},{"id":"1611.06310","title":"Local minima in training of neural networks","created":"2016-11-19","cited_by_count":19},{"id":"2006.06293","title":"Multiplicative noise and heavy tails in stochastic optimization","created":"2020-06-11","cited_by_count":17},{"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":"2606.05400","title":"LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization","created":"2026-06-03","cited_by_count":12},{"id":"2006.16297","title":"Optimization Landscape of Tucker Decomposition","created":"2020-06-29","cited_by_count":10},{"id":"2603.15929","title":"Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium","created":"2026-03-16","cited_by_count":9},{"id":"1812.06486","title":"Non-attracting Regions of Local Minima in Deep and Wide Neural Networks","created":"2018-12-16","cited_by_count":8},{"id":"2202.12262","title":"On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems","created":"2022-02-23","cited_by_count":8},{"id":"1710.11205","title":"Critical Points of Neural Networks: Analytical Forms and Landscape Properties","created":"2017-10-30","cited_by_count":7},{"id":"2504.02667","title":"Compositionality Unlocks Deep Interpretable Models","created":"2025-04-03","cited_by_count":6},{"id":"2301.12893","title":"Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq","created":"2023-01-30","cited_by_count":4},{"id":"2511.01137","title":"Regularization Implies balancedness in the deep linear network","created":"2025-11-03","cited_by_count":4},{"id":"1910.11923","title":"Learning Boolean Circuits with Neural Networks","created":"2019-10-25","cited_by_count":3},{"id":"2209.14358","title":"The minimal canonical form of a tensor network","created":"2022-09-28","cited_by_count":3},{"id":"2607.20503","title":"LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization","created":"2026-06-26","cited_by_count":3},{"id":"1706.02052","title":"Are Saddles Good Enough for Deep Learning?","created":"2017-06-07","cited_by_count":2},{"id":"2512.07766","title":"Formalized Hopfield Networks and Boltzmann Machines","created":"2025-12-08","cited_by_count":2}],"next_cursor":null}