no code implementations • 20 Nov 2023 • Gustavo Silva, Paul Rodriguez
In this manuscript, we introduce a new framework based on gradient histograms to analyze and justify important attributes of adaptive optimizers, such as their optimal performance and the relationships and dependencies among hyperparameters.
no code implementations • 19 Nov 2020 • Gustavo Silva, Paul Rodriguez
Convolutional sparse representation (CSR), shift-invariant model for inverse problems, has gained much attention in the fields of signal/image processing, machine learning and computer vision.
no code implementations • 20 Jul 2017 • Brendt Wohlberg, Paul Rodriguez
Two different approaches have recently been proposed for boundary handling in convolutional sparse representations, avoiding potential boundary artifacts arising from the circular boundary conditions implied by the use of frequency domain solution methods by introducing a spatial mask into the convolutional sparse coding problem.