{"total":29,"rows":[{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41,"area":null},{"id":"2110.03303","title":"Universal Approximation Under Constraints is Possible with Transformers","created":"2021-10-07","cited_by_count":32,"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":"2306.03303","title":"Global universal approximation of functional input maps on weighted spaces","created":"2023-06-05","cited_by_count":19,"area":null},{"id":"2306.03982","title":"Globally injective and bijective neural operators","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2207.08569","title":"Multi-manifold Attention for Vision Transformers","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2209.06788","title":"Small Transformers Compute Universal Metric Embeddings","created":"2022-09-14","cited_by_count":12,"area":null},{"id":"2201.09656","title":"A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations","created":"2021-12-17","cited_by_count":11,"area":null},{"id":"2209.10166","title":"Chaotic Hedging with Iterated Integrals and Neural Networks","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2304.00490","title":"Infinite-dimensional reservoir computing","created":"2023-04-02","cited_by_count":7,"area":null},{"id":"2204.11231","title":"Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?","created":"2022-04-24","cited_by_count":6,"area":null},{"id":"2105.07743","title":"Universal Regular Conditional Distributions","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2308.09250","title":"Capacity Bounds for Hyperbolic Neural Network Representations of Latent Tree Structures","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2411.00835","title":"Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2509.22969","title":"Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2111.09705","title":"Learning Free-Surface Flow with Physics-Informed Neural Networks","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2211.03627","title":"A Deep Double Ritz Method (D$^2$RM) for solving Partial Differential Equations using Neural Networks","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2105.09934","title":"Probing the Effect of Selection Bias on Generalization: A Thought Experiment","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2412.03393","title":"Can neural operators always be continuously discretized?","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2504.02321","title":"On shallow feedforward neural networks with inputs from a topological space","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2112.05673","title":"Neural Multi-Quantile Forecasting for Optimal Inventory Management","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2511.09902","title":"Autonomous-Flow-Based Generation","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2605.04255","title":"Entropic Riemannian Neural Optimal Transport","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2305.16639","title":"Universal Approximation and the Topological Neural Network","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2407.14957","title":"Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces","created":"2024-07-20","cited_by_count":0,"area":null},{"id":"2501.05930","title":"Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2602.23381","title":"Universality of shallow and deep neural networks on non-Euclidean spaces","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.23528","title":"Neural Operators Can Discover Functional Clusters","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2609.02727","title":"Neural operators approximate strongly continuous convex monotone semigroups","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}