{"total":64,"rows":[{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"area":null},{"id":"2101.08366","title":"Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs","created":"2021-01-20","cited_by_count":43,"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":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2302.04862","title":"Polynomial Neural Fields for Subband Decomposition and Manipulation","created":"2023-02-09","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2402.00949","title":"Geometry of Polynomial Neural Networks","created":"2024-02-01","cited_by_count":21,"area":null},{"id":"2501.18915","title":"Algebra Unveils Deep Learning -- An Invitation to Neuroalgebraic Geometry","created":"2025-01-31","cited_by_count":21,"area":null},{"id":"2110.06081","title":"On Expressivity and Trainability of Quadratic Networks","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2202.13473","title":"The Spectral Bias of Polynomial Neural Networks","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2304.05752","title":"Function Space and Critical Points of Linear Convolutional Networks","created":"2023-04-12","cited_by_count":19,"area":null},{"id":"2408.17221","title":"Geometry of Lightning Self-Attention: Identifiability and Dimension","created":"2024-08-30","cited_by_count":16,"area":null},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2408.04569","title":"Activation degree thresholds and expressiveness of polynomial neural networks","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2506.17093","title":"Identifiability of Deep Polynomial Neural Networks","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2410.00722","title":"On the Geometry and Optimization of Polynomial Convolutional Networks","created":"2024-10-01","cited_by_count":11,"area":null},{"id":"2101.09849","title":"Deep Learning Generalization and the Convex Hull of Training Sets","created":"2021-01-25","cited_by_count":10,"area":null},{"id":"2103.07016","title":"On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions","created":"2021-03-12","cited_by_count":10,"area":null},{"id":"2204.03039","title":"DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2411.03884","title":"Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models","created":"2024-11-06","cited_by_count":9,"area":null},{"id":"2505.11846","title":"Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2403.06235","title":"Probabilistic Neural Circuits","created":"2024-03-10","cited_by_count":7,"area":null},{"id":"2601.21645","title":"Identifiable Equivariant Networks are Layerwise Equivariant","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2303.06316","title":"One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks","created":"2023-03-11","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":"2511.19703","title":"The Alexander-Hirschowitz theorem for neurovarieties","created":"2025-11-24","cited_by_count":6,"area":null},{"id":"2305.13508","title":"DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2306.01271","title":"On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2206.05904","title":"Theoretical guarantees for the advantage of GNNs over NNs in generalizing bandlimited functions on Euclidean cubes","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2404.14674","title":"HOIN: High-Order Implicit Neural Representations","created":"2024-04-23","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":"2410.05465","title":"On the Expressive Power of Tree-Structured Probabilistic Circuits","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2505.11589","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2602.06105","title":"Robustness Verification of Polynomial Neural Networks","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.14037","title":"A Complete Symmetry Classification of Shallow ReLU Networks","created":"2026-04-15","cited_by_count":3,"area":null},{"id":"2106.13834","title":"Ladder Polynomial Neural Networks","created":"2021-06-25","cited_by_count":2,"area":null},{"id":"2110.10295","title":"Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2507.06367","title":"The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks","created":"2025-07-08","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":"2602.12390","title":"Rational Neural Networks have Expressivity Advantages","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.29566","title":"The Geometry of Polynomial Group Convolutional Neural Networks","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2607.13749","title":"Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2203.10366","title":"Deep Learning Generalization, Extrapolation, and Over-parameterization","created":"2022-03-19","cited_by_count":1,"area":null},{"id":"2406.02336","title":"Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2408.07815","title":"Algebraic Representations for Faster Predictions in Convolutional Neural Networks","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2604.15632","title":"Algebraic Invariants of Lightning Self-Attention","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.09609","title":"Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2606.23587","title":"It's Much Easier for Neural Networks to learn Game of Life Dynamics with the Right Activation Function: Polynomial Kolmogorov-Arnold Networks","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.20887","title":"TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2307.10892","title":"Learning and Generalizing Polynomials in Simulation Metamodeling","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2401.01801","title":"A quatum inspired neural network for geometric modeling","created":"2024-01-03","cited_by_count":0,"area":null},{"id":"2410.19844","title":"A practical, fast method for solving sum-of-squares problems for very large polynomials","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2502.01247","title":"Polynomial, trigonometric, and tropical activations","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2511.21414","title":"SUPN: Shallow Universal Polynomial Networks for Efficient Function Approximation","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.04264","title":"Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.14737","title":"Parameter-Minimal Neural DE Solvers via Horner Polynomials","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2606.28464","title":"Singular Learning and Occam's Razor in Deep Monomial Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.21094","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.20183","title":"Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.28500","title":"Algebraic Expressivity Certificates for Shallow Polynomial Neural Networks","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.09620","title":"The Identifiability and Observability of Deep Normalized Attention","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.20069","title":"Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}