{"total":47,"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":"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":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2209.03525","title":"Implicit Full Waveform Inversion with Deep Neural Representation","created":"2022-09-08","cited_by_count":26,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2101.08303","title":"From Local Pseudorandom Generators to Hardness of Learning","created":"2021-01-20","cited_by_count":24,"area":null},{"id":"2306.16361","title":"Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time","created":"2023-06-28","cited_by_count":20,"area":null},{"id":"2206.01342","title":"Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2405.20236","title":"Disentangling and Mitigating the Impact of Task Similarity for Continual Learning","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2106.01101","title":"Learning a Single Neuron with Bias Using Gradient Descent","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2305.19510","title":"Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2107.10370","title":"Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II","created":"2021-07-21","cited_by_count":16,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2202.08064","title":"Learning a Single Neuron for Non-monotonic Activation Functions","created":"2022-02-16","cited_by_count":13,"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":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2107.10868","title":"Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time","created":"2021-07-22","cited_by_count":10,"area":null},{"id":"2210.06088","title":"Annihilation of Spurious Minima in Two-Layer ReLU Networks","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2311.01644","title":"Should Under-parameterized Student Networks Copy or Average Teacher Weights?","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2404.18769","title":"Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2506.02269","title":"A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2206.02139","title":"Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks","created":"2022-06-05","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","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":"2411.14349","title":"Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2405.07098","title":"Interpretable global minima of deep ReLU neural networks on sequentially separable data","created":"2024-05-11","cited_by_count":4,"area":null},{"id":"2502.16021","title":"Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2201.04194","title":"Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics","created":"2022-01-11","cited_by_count":3,"area":null},{"id":"2209.15265","title":"Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2509.19773","title":"Sobolev acceleration for neural networks","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2111.15256","title":"Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks","created":"2021-11-30","cited_by_count":2,"area":null},{"id":"2112.11018","title":"A Theoretical View of Linear Backpropagation and Its Convergence","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2312.16819","title":"Hidden Minima in Two-Layer ReLU Networks","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2401.03214","title":"Understanding Representation Learnability of Nonlinear Self-Supervised Learning","created":"2024-01-06","cited_by_count":2,"area":null},{"id":"2601.00455","title":"Deep Networks Learn Deep Hierarchical Models","created":"2026-01-01","cited_by_count":2,"area":null},{"id":"2401.07606","title":"RedEx: Beyond Fixed Representation Methods via Convex Optimization","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2608.06766","title":"Hidden Gauge Controls Feature Specialization in ReLU Networks","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2501.07400","title":"Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2512.06347","title":"Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2610.01728","title":"Removing spurious minima for planar features by skip connections","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}