{"total":97,"rows":[{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2105.00304","title":"SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects","created":"2021-05-01","cited_by_count":104,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"area":null},{"id":"2102.02416","title":"An end-to-end trainable hybrid classical-quantum classifier","created":"2021-02-04","cited_by_count":51,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"area":null},{"id":"2202.07626","title":"Random Feature Amplification: Feature Learning and Generalization in Neural Networks","created":"2022-02-15","cited_by_count":35,"area":null},{"id":"2205.01510","title":"ExSpliNet: An interpretable and expressive spline-based neural network","created":"2022-05-03","cited_by_count":33,"area":null},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2108.00089","title":"Tensor-Train Density Estimation","created":"2021-07-30","cited_by_count":30,"area":null},{"id":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","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":"2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","created":"2021-05-31","cited_by_count":25,"area":null},{"id":"2205.11691","title":"High-Order Pooling for Graph Neural Networks with Tensor Decomposition","created":"2022-05-24","cited_by_count":24,"area":null},{"id":"2409.07953","title":"What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?","created":"2024-09-12","cited_by_count":22,"area":null},{"id":"2102.01621","title":"Depth separation beyond radial functions","created":"2021-02-02","cited_by_count":18,"area":null},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18,"area":null},{"id":"2102.10492","title":"Deep ReLU Networks Preserve Expected Length","created":"2021-02-21","cited_by_count":17,"area":null},{"id":"2203.09255","title":"On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2305.19440","title":"Machine learning with tree tensor networks, CP rank constraints, and tensor dropout","created":"2023-05-30","cited_by_count":15,"area":null},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2202.11749","title":"Are All Linear Regions Created Equal?","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2206.06597","title":"Permutation Search of Tensor Network Structures via Local Sampling","created":"2022-06-14","cited_by_count":13,"area":null},{"id":"2507.12549","title":"The Serial Scaling Hypothesis","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2111.08117","title":"Neural networks with linear threshold activations: structure and algorithms","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2112.09747","title":"A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation","created":"2021-12-17","cited_by_count":12,"area":null},{"id":"2211.13866","title":"Minimal Width for Universal Property of Deep RNN","created":"2022-11-25","cited_by_count":12,"area":null},{"id":"2211.16494","title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","created":"2022-11-29","cited_by_count":12,"area":null},{"id":"2401.12007","title":"Tensor-view Topological Graph Neural Network","created":"2024-01-22","cited_by_count":12,"area":null},{"id":"2506.17093","title":"Identifiability of Deep Polynomial Neural Networks","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2303.13565","title":"Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2111.01356","title":"DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method","created":"2021-11-02","cited_by_count":9,"area":null},{"id":"2310.20498","title":"Generative Learning of Continuous Data by Tensor Networks","created":"2023-10-31","cited_by_count":9,"area":null},{"id":"2104.05758","title":"Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2106.14749","title":"A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2110.07631","title":"More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2104.05048","title":"Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification","created":"2021-04-11","cited_by_count":6,"area":null},{"id":"2110.14538","title":"Reinforcement Learning in Factored Action Spaces using Tensor Decompositions","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2206.10581","title":"Nimble GNN Embedding with Tensor-Train Decomposition","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2301.09245","title":"Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks","created":"2023-01-23","cited_by_count":6,"area":null},{"id":"2307.04001","title":"Polynomial Width is Sufficient for Set Representation with High-dimensional Features","created":"2023-07-08","cited_by_count":6,"area":null},{"id":"2106.15666","title":"Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2405.04590","title":"Language Modeling Using Tensor Trains","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2410.05626","title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","created":"2024-10-08","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":"2103.11785","title":"Entangled q-Convolutional Neural Nets","created":"2021-03-06","cited_by_count":4,"area":null},{"id":"2106.04741","title":"Marginalizable Density Models","created":"2021-06-08","cited_by_count":4,"area":null},{"id":"2303.11249","title":"What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2308.14418","title":"Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2403.09728","title":"Simulating Weighted Automata over Sequences and Trees with Transformers","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2101.04869","title":"Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications","created":"2021-01-13","cited_by_count":3,"area":null},{"id":"2205.10760","title":"CNNs Avoid Curse of Dimensionality by Learning on Patches","created":"2022-05-22","cited_by_count":3,"area":null},{"id":"2310.07136","title":"Exponential Quantum Communication Advantage in Distributed Inference and Learning","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2403.19500","title":"Tensor Network-Constrained Kernel Machines as Gaussian Processes","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2406.05045","title":"A Tensor Decomposition Perspective on Second-order RNNs","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2410.15241","title":"Conditional Uncertainty Quantification for Tensorized Topological Neural Networks","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2410.15247","title":"Tensor-Fused Multi-View Graph Contrastive Learning","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2504.11130","title":"Divergence of Empirical Neural Tangent Kernel in Classification Problems","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2105.14620","title":"Patch Tracking-based Streaming Tensor Ring Completion for Visual Data Recovery","created":"2021-05-30","cited_by_count":2,"area":null},{"id":"2107.01081","title":"Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning","created":"2021-07-02","cited_by_count":2,"area":null},{"id":"2108.10825","title":"Adaptive Group Lasso Neural Network Models for Functions of Few Variables and Time-Dependent Data","created":"2021-08-24","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2111.14046","title":"Neural Tangent Kernel of Matrix Product States: Convergence and Applications","created":"2021-11-28","cited_by_count":2,"area":null},{"id":"2203.04352","title":"TTML: tensor trains for general supervised machine learning","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2209.02088","title":"A variational neural network approach for glacier modelling with nonlinear rheology","created":"2022-09-05","cited_by_count":2,"area":null},{"id":"2209.09098","title":"Deep tensor networks with matrix product operators","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2310.03529","title":"Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2405.13682","title":"Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2508.18408","title":"Low-Rank Tensor Decompositions for the Theory of Neural Networks","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.08570","title":"Who Said Neural Networks Aren't Linear?","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2607.20811","title":"New Complexity-Theoretic Frontiers of Tractability for Neural Network Training","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2106.11827","title":"Lower and Upper Bounds on the VC-Dimension of Tensor Network Models","created":"2021-06-22","cited_by_count":1,"area":null},{"id":"2303.03544","title":"Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2306.02560","title":"Tensorized Hypergraph Neural Networks","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2306.06146","title":"Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers","created":"2023-06-09","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":"2410.20439","title":"TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting","created":"2024-10-27","cited_by_count":1,"area":null},{"id":"2603.13872","title":"On Interpolation Formulas Describing Neural Network Generalization","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2607.13246","title":"Reassessing Muon for Matrix Factorization","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2103.14998","title":"Tensor Networks for Multi-Modal Non-Euclidean Data","created":"2021-03-27","cited_by_count":0,"area":null},{"id":"2106.12532","title":"Bayesian Deep Learning Hyperparameter Search for Robust Function Mapping to Polynomials with Noise","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2106.13542","title":"Tensor-based framework for training flexible neural networks","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2112.13551","title":"Learning Robust and Lightweight Model through Separable Structured Transformations","created":"2021-12-27","cited_by_count":0,"area":null},{"id":"2204.13991","title":"Physical Deep Learning with Biologically Plausible Training Method","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2411.01763","title":"How Analysis Can Teach Us the Optimal Way to Design Neural Operators","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2412.19836","title":"Reduced Order Models and Conditional Expectation -- Analysing Parametric Low-Order Approximations","created":"2024-12-22","cited_by_count":0,"area":null},{"id":"2502.06300","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2503.22082","title":"ReLU Networks as Random Functions: Their Distribution in Probability Space","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2509.23348","title":"Entering the Era of Discrete Diffusion Models: A Benchmark for Schr\\\"odinger Bridges and Entropic Optimal Transport","created":"2025-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2510.15425","title":"TeamFormer: Shallow Parallel Transformers with Progressive Approximation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2604.02201","title":"On the Role of Depth in the Expressivity of RNNs","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.15183","title":"When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability","created":"2026-05-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}