{"total":60,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"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,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2201.00217","title":"Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces","created":"2022-01-01","cited_by_count":45,"area":null},{"id":"2205.02956","title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","created":"2022-05-05","cited_by_count":38,"area":null},{"id":"2212.03130","title":"Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems","created":"2022-12-06","cited_by_count":34,"area":null},{"id":"2109.02832","title":"Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks","created":"2021-09-07","cited_by_count":32,"area":null},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30,"area":null},{"id":"2205.13863","title":"Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power","created":"2022-05-27","cited_by_count":23,"area":null},{"id":"2107.00896","title":"Theory of Deep Convolutional Neural Networks III: Approximating Radial Functions","created":"2021-07-02","cited_by_count":22,"area":null},{"id":"2201.13094","title":"Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2506.10959","title":"Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods","created":"2025-06-12","cited_by_count":15,"area":null},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2301.00008","title":"Effects of Data Geometry in Early Deep Learning","created":"2022-12-29","cited_by_count":12,"area":null},{"id":"2307.12461","title":"Rates of Approximation by ReLU Shallow Neural Networks","created":"2023-07-24","cited_by_count":12,"area":null},{"id":"2402.03979","title":"Cross Entropy versus Label Smoothing: A Neural Collapse Perspective","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2303.09863","title":"Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2210.10443","title":"Deep neural network expressivity for optimal stopping problems","created":"2022-10-19","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":"2208.10570","title":"Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders","created":"2022-08-22","cited_by_count":8,"area":null},{"id":"2304.04443","title":"Approximation of Nonlinear Functionals Using Deep ReLU Networks","created":"2023-04-10","cited_by_count":8,"area":null},{"id":"2310.00545","title":"Implicit Neural Representations and the Algebra of Complex Wavelets","created":"2023-10-01","cited_by_count":8,"area":null},{"id":"2103.00542","title":"Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on H\\\"older Class","created":"2021-02-28","cited_by_count":7,"area":null},{"id":"2209.08399","title":"Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$","created":"2022-09-17","cited_by_count":7,"area":null},{"id":"2404.03761","title":"Learning smooth functions in high dimensions: from sparse polynomials to deep neural networks","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2203.00614","title":"Side Effects of Learning from Low-dimensional Data Embedded in a Euclidean Space","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2206.04569","title":"Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2112.09181","title":"Approximation of functions with one-bit neural networks","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2505.03205","title":"Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2111.14039","title":"Generalization Performance of Empirical Risk Minimization on Over-parameterized Deep ReLU Nets","created":"2021-11-28","cited_by_count":4,"area":null},{"id":"2202.01919","title":"Theoretical Exploration of Solutions of Feedforward ReLU Networks","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2307.16203","title":"Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning","created":"2023-07-30","cited_by_count":4,"area":null},{"id":"2308.08030","title":"Classification of Data Generated by Gaussian Mixture Models Using Deep ReLU Networks","created":"2023-08-15","cited_by_count":4,"area":null},{"id":"2505.24205","title":"On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks","created":"2025-05-30","cited_by_count":4,"area":"moe"},{"id":"2206.00934","title":"Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2307.02478","title":"Linear Regression on Manifold Structured Data: the Impact of Extrinsic Geometry on Solutions","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2406.11463","title":"Just How Flexible are Neural Networks in Practice?","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2503.04263","title":"Bi-Lipschitz Ansatz for Anti-Symmetric Functions","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2110.09163","title":"A Dimensionality Reduction Approach for Convolutional Neural Networks","created":"2021-10-18","cited_by_count":2,"area":null},{"id":"2210.00805","title":"Limitations of neural network training due to numerical instability of backpropagation","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2309.04860","title":"Approximation Results for Gradient Descent trained Neural Networks","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2408.05540","title":"Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks","created":"2024-08-10","cited_by_count":2,"area":null},{"id":"2201.12052","title":"Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2208.07498","title":"Universal Solutions of Feedforward ReLU Networks for Interpolations","created":"2022-08-16","cited_by_count":1,"area":null},{"id":"2311.08845","title":"Statistical learning by sparse deep neural networks","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2409.14174","title":"Component-based Sketching for Deep ReLU Nets","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2602.20370","title":"Quantitative Approximation Rates for Group Equivariant Learning","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2604.06774","title":"Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2301.00009","title":"On the Geometry of Reinforcement Learning in Continuous State and Action Spaces","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2302.00160","title":"Local transfer learning from one data space to another","created":"2023-02-01","cited_by_count":0,"area":null},{"id":"2303.15464","title":"Mathematical Challenges in Deep Learning","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2409.17991","title":"Dimension-independent learning rates for high-dimensional classification problems","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2503.18676","title":"Feature Qualification by Deep Nets: A Constructive Approach","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2504.16682","title":"Provable wavelet-based neural approximation","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2509.22748","title":"Generalization Analysis for Classification on Korobov Space","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2512.09853","title":"New Approximation Results and Optimal Estimation for Fully Connected Deep Neural Networks","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.00511","title":"Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions","created":"2026-01-31","cited_by_count":0,"area":null}],"next_cursor":null}