3 papers
cs.LG2025
Implicit Regularization of the Deep Inverse Prior Trained with Inertia
Nathan Buskulic, Jalal Fadil, Yvain Quéau
Solving inverse problems with neural networks benefits from very few theoretical guarantees when it comes to the recovery guarantees. We provide in this work convergence and recove…
cs.LG2024
Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems trained with Gradient Descent
Nathan Buskulic, Jalal Fadili, Yvain Quéau
Advanced machine learning methods, and more prominently neural networks, have become standard to solve inverse problems over the last years. However, the theoretical recovery guara…
cs.LG2023
Convergence Guarantees of Overparametrized Wide Deep Inverse Prior
Nathan Buskulic, Yvain Quéau, Jalal Fadili
Neural networks have become a prominent approach to solve inverse problems in recent years. Amongst the different existing methods, the Deep Image/Inverse Priors (DIPs) technique i…