Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
From MaRDI portal
Publication:5027040
DOI10.1137/19M1272780OpenAlexW3039780279MaRDI QIDQ5027040
Patrick L. Combettes, Jean-Christophe Pesquet
Publication date: 3 February 2022
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1903.01014
Variational methods involving nonlinear operators (47J30) Neural networks for/in biological studies, artificial life and related topics (92B20) Contraction-type mappings, nonexpansive mappings, (A)-proper mappings, etc. (47H09)
Related Items
CLIP: cheap Lipschitz training of neural networks, Wasserstein-Based Projections with Applications to Inverse Problems, Adversarial Robustness of Sparse Local Lipschitz Predictors, Convergence of deep convolutional neural networks, Connections between numerical algorithms for PDEs and neural networks, NESTANets: stable, accurate and efficient neural networks for analysis-sparse inverse problems, Convolutional proximal neural networks and plug-and-play algorithms, On \(\alpha\)-firmly nonexpansive operators in \(r\)-uniformly convex spaces, Learning Maximally Monotone Operators for Image Recovery, Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A primal-dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms
- A dynamical system associated with the fixed points set of a nonexpansive operator
- Sharp convergence rates for averaged nonexpansive maps
- The forward-backward algorithm and the normal problem
- Deep neural network structures solving variational inequalities
- Convergence Rate Analysis for Averaged Fixed Point Iterations in Common Fixed Point Problems
- Easily Parallelizable and Distributable Class of Algorithms for Structured Sparsity, with Optimal Acceleration
- Proximal Thresholding Algorithm for Minimization over Orthonormal Bases
- Quasi-Nonexpansive Iterations on the Affine Hull of Orbits: From Mann's Mean Value Algorithm to Inertial Methods
- On the Convergence of the Iterative Shrinkage/Thresholding Algorithm With a Weakly Convex Penalty
- Robust Large Margin Deep Neural Networks
- Solving monotone inclusions via compositions of nonexpansive averaged operators
- Lipschitz properties for deep convolutional networks
- Finite-Dimensional Variational Inequalities and Complementarity Problems
- Optimal Approximation with Sparsely Connected Deep Neural Networks
- Deep unfolding of a proximal interior point method for image restoration
- Distributed Generalized Nash Equilibria Computation of Monotone Games via Double-Layer Preconditioned Proximal-Point Algorithms
- Nonexpansiveness of a linearized augmented Lagrangian operator for hierarchical convex optimization
- Signal Recovery by Proximal Forward-Backward Splitting
- Monotone Operator Methods for Nash Equilibria in Non-potential Games
- Convex analysis and monotone operator theory in Hilbert spaces
