{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"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":"2101.10423","title":"Online Continual Learning in Image Classification: An Empirical Survey","created":"2021-01-25","cited_by_count":245},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2010.04495","title":"Linear Mode Connectivity in Multitask and Continual Learning","created":"2020-10-09","cited_by_count":145},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"1909.05989","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","created":"2019-09-13","cited_by_count":115},{"id":"1803.01719","title":"How to Start Training: The Effect of Initialization and Architecture","created":"2018-03-05","cited_by_count":109},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"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":"2010.04003","title":"A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix","created":"2020-10-07","cited_by_count":103},{"id":"2310.02244","title":"Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks","created":"2023-10-03","cited_by_count":97},{"id":"1801.03744","title":"Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?","created":"2018-01-11","cited_by_count":94},{"id":"2211.12701","title":"Continual Learning of Natural Language Processing Tasks: A Survey","created":"2022-11-23","cited_by_count":83},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81},{"id":"2302.05836","title":"Theory on Forgetting and Generalization of Continual Learning","created":"2023-02-12","cited_by_count":72},{"id":"2006.11942","title":"Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent","created":"2020-06-21","cited_by_count":68},{"id":"2309.16620","title":"Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit","created":"2023-09-28","cited_by_count":66},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64},{"id":"2110.01765","title":"Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping","created":"2021-10-05","cited_by_count":52},{"id":"2010.12859","title":"Stable ResNet","created":"2020-10-24","cited_by_count":49},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46},{"id":"2305.18411","title":"Feature-Learning Networks Are Consistent Across Widths At Realistic Scales","created":"2023-05-28","cited_by_count":41},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39},{"id":"2202.10203","title":"Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning","created":"2022-02-21","cited_by_count":29},{"id":"2207.06475","title":"Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime","created":"2022-06-01","cited_by_count":29},{"id":"2106.06615","title":"Precise characterization of the prior predictive distribution of deep ReLU networks","created":"2021-06-11","cited_by_count":28},{"id":"2401.12617","title":"The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model","created":"2024-01-23","cited_by_count":26},{"id":"2206.12314","title":"Learning sparse features can lead to overfitting in neural networks","created":"2022-06-24","cited_by_count":23},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23},{"id":"2407.10315","title":"Order parameters and phase transitions of continual learning in deep neural networks","created":"2024-07-14","cited_by_count":14},{"id":"2409.18061","title":"Optimal Protocols for Continual Learning via Statistical Physics and Control Theory","created":"2024-09-26","cited_by_count":14},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13}],"next_cursor":null}