{"total":23,"rows":[{"id":"2109.11676","title":"Theory of overparametrization in quantum neural networks","created":"2021-09-23","cited_by_count":100,"area":null},{"id":"2105.14835","title":"Towards Lower Bounds on the Depth of ReLU Neural Networks","created":"2021-05-31","cited_by_count":56,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2303.17045","title":"Training Neural Networks is NP-Hard in Fixed Dimension","created":"2023-03-29","cited_by_count":23,"area":null},{"id":"2105.08675","title":"The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality","created":"2021-05-18","cited_by_count":22,"area":null},{"id":"2204.01368","title":"Training Fully Connected Neural Networks is $\\exists\\mathbb{R}$-Complete","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","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":"2402.03625","title":"Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2312.12657","title":"The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2305.11833","title":"Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2205.01480","title":"Multi-Spatio-temporal Fusion Graph Recurrent Network for Traffic forecasting","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2205.01940","title":"Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs","created":"2022-05-04","cited_by_count":2,"area":null},{"id":"2311.10972","title":"Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes","created":"2023-11-18","cited_by_count":2,"area":null},{"id":"2411.06848","title":"Generative Feature Training of Thin 2-Layer Networks","created":"2024-11-11","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":"2302.14744","title":"Tight Mixed-Integer Optimization Formulations for Prescriptive Trees","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2602.19172","title":"Online Realizable Regression and Applications for ReLU Networks","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2102.09798","title":"Training Neural Networks is $\\exists\\mathbb R$-complete","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2311.08655","title":"Review of AlexNet for Medical Image Classification","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2508.17783","title":"Algebraic Approach to Ridge-Regularized Mean Squared Error Minimization in Minimal ReLU Neural Network","created":"2025-08-25","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":"2609.27932","title":"Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}