MultiComposite Nonconvex Optimization for Training Deep Neural Networks
From MaRDI portal
Publication:5114402
DOI10.1137/18M1231559zbMath1445.90086OpenAlexW3036100489MaRDI QIDQ5114402
Ying Cui, Ziyu He, Jong-Shi Pang
Publication date: 22 June 2020
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/18m1231559
nonconvexityexact penalizationmajorization-minimizationsemismooth Newton methodnondifferentiablitydeep neural network
Related Items
Nonconvex and nonsmooth approaches for affine chance-constrained stochastic programs, Linearly Constrained Nonsmooth Optimization for Training Autoencoders, Learning-informed parameter identification in nonlinear time-dependent PDEs, Markov chain stochastic DCA and applications in deep learning with PDEs regularization, Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks, Open issues and recent advances in DC programming and DCA, Lifted stationary points of sparse optimization with complementarity constraints, Nonconvex robust programming via value-function optimization
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Partial penalization for the solution of generalized Nash equilibrium problems
- Convex analysis approach to d. c. programming: Theory, algorithms and applications
- Multilayer feedforward networks are universal approximators
- A globally convergent Newton method for convex \(SC^ 1\) minimization problems
- Deterministic global optimization. Theory, methods and applications
- Stochastic subgradient method converges on tame functions
- Introduction to Piecewise Differentiable Equations
- Computing B-Stationary Points of Nonsmooth DC Programs
- Exact penalization via dini and hadamard conditional derivatives
- Composite Difference-Max Programs for Modern Statistical Estimation Problems
- Stochastic Model-Based Minimization of Weakly Convex Functions
- Optimization Methods for Large-Scale Machine Learning
- Finite-Dimensional Variational Inequalities and Complementarity Problems
- ADMM for multiaffine constrained optimization
- Computing the Best Approximation over the Intersection of a Polyhedral Set and the Doubly Nonnegative Cone
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- A Fast Learning Algorithm for Deep Belief Nets
- A Stochastic Approximation Method