Date
Thu, 06 Mar 2025
Time
12:00 - 12:30
Location
Lecture room 5
Speaker
Vicky Kouni
Organisation
Mathematical Institute (University of Oxford)

We present a new ensemble framework for boosting the performance of overparameterized unfolding networks solving the compressed sensing problem. We combine a state-of-the-art overparameterized unfolding network with a continuation technique, to warm-start a crucial quantity of the said network's architecture; we coin the resulting continued network C-DEC. Moreover, for training and evaluating C-DEC, we incorporate the log-cosh loss function, which enjoys both linear and quadratic behavior. Finally, we numerically assess C-DEC's performance on real-world images. Results showcase that the combination of continuation with the overparameterized unfolded architecture, trained and evaluated with the chosen loss function, yields smoother loss landscapes and improved reconstruction and generalization performance of C-DEC, consistently for all datasets.

Last updated on 4 Mar 2025, 5:41pm. Please contact us with feedback and comments about this page.