{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97},{"id":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"1908.01580","title":"The HSIC Bottleneck: Deep Learning without Back-Propagation","created":"2019-08-05","cited_by_count":77},{"id":"1704.08045","title":"The loss surface of deep and wide neural networks","created":"2017-04-26","cited_by_count":74},{"id":"2202.05928","title":"Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data","created":"2022-02-11","cited_by_count":74},{"id":"1802.09766","title":"Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle","created":"2018-02-27","cited_by_count":70},{"id":"2002.07867","title":"Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology","created":"2020-02-18","cited_by_count":66},{"id":"2402.15555","title":"Deep Networks Always Grok and Here is Why","created":"2024-02-23","cited_by_count":51},{"id":"2303.06173","title":"Unifying Grokking and Double Descent","created":"2023-03-10","cited_by_count":50},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","cited_by_count":48},{"id":"2305.13165","title":"Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model","created":"2023-05-22","cited_by_count":43},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39},{"id":"2003.09671","title":"On Information Plane Analyses of Neural Network Classifiers -- A Review","created":"2020-03-21","cited_by_count":37},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35},{"id":"2310.02541","title":"Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data","created":"2023-10-04","cited_by_count":33},{"id":"1606.00304","title":"Efficient multivariate entropy estimation via $k$-nearest neighbour distances","created":"2016-06-01","cited_by_count":28},{"id":"2006.07123","title":"Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks","created":"2020-06-12","cited_by_count":25},{"id":"2310.16441","title":"Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding","created":"2023-10-25","cited_by_count":25},{"id":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22},{"id":"2412.09810","title":"The Complexity Dynamics of Grokking","created":"2024-12-13","cited_by_count":22},{"id":"2106.02734","title":"Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness","created":"2021-06-04","cited_by_count":20},{"id":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19},{"id":"2410.04887","title":"Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse","created":"2024-10-07","cited_by_count":16},{"id":"2106.12912","title":"Information Bottleneck: Exact Analysis of (Quantized) Neural Networks","created":"2021-06-24","cited_by_count":15},{"id":"2305.00380","title":"DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning","created":"2023-04-30","cited_by_count":15},{"id":"2310.05918","title":"Grokking as Compression: A Nonlinear Complexity Perspective","created":"2023-10-09","cited_by_count":14},{"id":"2405.14630","title":"Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension","created":"2024-05-23","cited_by_count":13},{"id":"2210.04311","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","created":"2022-10-09","cited_by_count":12},{"id":"2410.04489","title":"Grokking at the Edge of Linear Separability","created":"2024-10-06","cited_by_count":12},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8},{"id":"2509.17738","title":"Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking","created":"2025-09-22","cited_by_count":8},{"id":"2501.19104","title":"Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime","created":"2025-01-31","cited_by_count":4},{"id":"2312.06887","title":"Understanding and Leveraging the Learning Phases of Neural Networks","created":"2023-12-11","cited_by_count":2},{"id":"2504.12700","title":"A Two-Phase Perspective on Deep Learning Dynamics","created":"2025-04-17","cited_by_count":1}],"next_cursor":null}