Search Results for author:
Found 7 papers, 4 papers with code
Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms
We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus.
A Neural-Network-Based Convex Regularizer for Inverse Problems
The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality.
Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions
Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community.
Delaunay-Triangulation-Based Learning with Hessian Total-Variation Regularization
Rectified linear unit (ReLU) neural networks generate continuous and piecewise-linear (CPWL) mappings and are the state-of-the-art approach for solving regression problems.
On the Number of Regions of Piecewise Linear Neural Networks
We first provide upper and lower bounds on the maximal number of linear regions of a CPWL NN given its depth, width, and the number of linear regions of its activation functions.
Approximation of Lipschitz Functions using Deep Spline Neural Networks
Lipschitz-constrained neural networks have many applications in machine learning.
Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods
We show that averaged denoising operators built from 1-Lipschitz deep spline networks consistently outperform those built from 1-Lipschitz ReLU networks.
