{"total":14,"rows":[{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2107.05680","title":"Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions","created":"2021-07-12","cited_by_count":14,"area":null},{"id":"2110.06488","title":"The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program","created":"2021-10-13","cited_by_count":11,"area":null},{"id":"2110.06482","title":"Parallel Deep Neural Networks Have Zero Duality Gap","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2205.13098","title":"Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization","created":"2022-05-26","cited_by_count":9,"area":null},{"id":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2105.01420","title":"Training Quantized Neural Networks to Global Optimality via Semidefinite Programming","created":"2021-05-04","cited_by_count":6,"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":"2207.13120","title":"Analysis and Design of Quadratic Neural Networks for Regression, Classification, and Lyapunov Control of Dynamical Systems","created":"2022-07-26","cited_by_count":1,"area":null},{"id":"2405.14033","title":"Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2411.08267","title":"Least Squares Training of Quadratic Convolutional Neural Networks with Applications to System Theory","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2602.19017","title":"Why ReLU? A Bit-Model Dichotomy for Deep Network Training","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2609.17654","title":"Regularized Least Squares Training of Quadratic Neural Networks with Applications to System Identification","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}