{"total":43,"rows":[{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256,"area":null},{"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,"area":null},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78,"area":null},{"id":"2105.04550","title":"Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth","created":"2021-05-10","cited_by_count":55,"area":null},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2107.06608","title":"Continuous vs. Discrete Optimization of Deep Neural Networks","created":"2021-07-14","cited_by_count":34,"area":null},{"id":"2106.03970","title":"Batch Normalization Orthogonalizes Representations in Deep Random Networks","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2110.12661","title":"ZerO Initialization: Initializing Neural Networks with only Zeros and Ones","created":"2021-10-25","cited_by_count":28,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2205.14612","title":"Do Residual Neural Networks discretize Neural Ordinary Differential Equations?","created":"2022-05-29","cited_by_count":27,"area":null},{"id":"2105.14417","title":"Overparameterization of deep ResNet: zero loss and mean-field analysis","created":"2021-05-30","cited_by_count":24,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"area":null},{"id":"2203.16462","title":"Convergence of gradient descent for deep neural networks","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2108.02040","title":"Convergence of gradient descent for learning linear neural networks","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2405.13456","title":"Deep linear networks for regression are implicitly regularized towards flat minima","created":"2024-05-22","cited_by_count":17,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2204.10782","title":"On Feature Learning in Neural Networks with Global Convergence Guarantees","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2502.17494","title":"External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2208.02711","title":"Agnostic Learning of General ReLU Activation Using Gradient Descent","created":"2022-08-04","cited_by_count":12,"area":null},{"id":"2106.14836","title":"Understanding Dynamics of Nonlinear Representation Learning and Its Application","created":"2021-06-28","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2209.09315","title":"Deep Linear Networks can Benignly Overfit when Shallow Ones Do","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2403.12887","title":"Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2210.05371","title":"On skip connections and normalisation layers in deep optimisation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2509.25351","title":"Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2506.05249","title":"On the Convergence of Gradient Descent on Learning Transformers with Residual Connections","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2307.01177","title":"Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2402.09084","title":"Sobolev Training for Operator Learning","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2503.04626","title":"IDInit: A Universal and Stable Initialization Method for Neural Network Training","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2204.07261","title":"Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2309.01796","title":"Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2206.15058","title":"A note on Linear Bottleneck networks and their Transition to Multilinearity","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2408.13767","title":"Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2502.11152","title":"Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2605.10775","title":"On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2201.02761","title":"Global Convergence Analysis of Deep Linear Networks with A One-neuron Layer","created":"2022-01-08","cited_by_count":0,"area":null}],"next_cursor":null}