Bangti Jin

activity

20232026

most citedEarly Stopping of Untrained Convolutional Neural Networks

1 citations · 1 across the 7 of their papers we have counts for

collaborators

Showing 2024Show all

2 papers · 1 filter

math.NA2024

Theory and Fast Learned Solver for $ℓ^{1}$ -TV Regularization

Xinling Liu, Jianjun Wang, Bangti Jin

The $ℓ^{1}$ and total variation (TV) penalties have been used successfully in many areas, and the combination of the $ℓ^{1}$ and TV penalties can lead to further improved perform…

math.NA2024★ 1 cited

Early Stopping of Untrained Convolutional Neural Networks

Tim Jahn, Bangti Jin

In recent years, new regularization methods based on (deep) neural networks have shown very promising empirical performance for the numerical solution of ill-posed problems, e.g.,…

Theory and Fast Learned Solver for ℓ1-TV Regularization

Early Stopping of Untrained Convolutional Neural Networks

Theory and Fast Learned Solver for $ℓ^{1}$ -TV Regularization