Artikel mit Open-Access-Mandaten - Tolga ErgenWeitere Informationen
Verfügbar: 9
Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks
M Pilanci, T Ergen
International Conference on Machine Learning, 7695-7705, 2020
Mandate: US National Science Foundation
Revealing the Structure of Deep Neural Networks via Convex Duality
T Ergen, M Pilanci
arXiv preprint arXiv:2002.09773, 2020
Mandate: US National Science Foundation
Convex geometry and duality of over-parameterized neural networks
T Ergen, M Pilanci
Journal of machine learning research 22 (212), 1-63, 2021
Mandate: US National Science Foundation, US Department of Defense
Global optimality beyond two layers: Training deep relu networks via convex programs
T Ergen, M Pilanci
International Conference on Machine Learning, 2993-3003, 2021
Mandate: US National Science Foundation
Unraveling attention via convex duality: Analysis and interpretations of vision transformers
A Sahiner, T Ergen, B Ozturkler, J Pauly, M Mardani, M Pilanci
International Conference on Machine Learning, 19050-19088, 2022
Mandate: US National Science Foundation, US Department of Defense, US National …
Path regularization: A convexity and sparsity inducing regularization for parallel relu networks
T Ergen, M Pilanci
Advances in Neural Information Processing Systems 36, 2024
Mandate: US National Science Foundation, US Department of Defense
Convex optimization for shallow neural networks
T Ergen, M Pilanci
2019 57th Annual Allerton Conference on Communication, Control, and …, 2019
Mandate: US National Science Foundation
A novel distributed anomaly detection algorithm based on support vector machines
T Ergen, SS Kozat
Digital Signal Processing 99, 102657, 2020
Mandate: Scientific and Technological Research Council of Turkey
Fixing the NTK: from neural network linearizations to exact convex programs
RV Dwaraknath, T Ergen, M Pilanci
Advances in Neural Information Processing Systems 36, 2024
Mandate: US National Science Foundation, US Department of Defense
Angaben zur Publikation und Finanzierung werden automatisch von einem Computerprogramm ermittelt