Convex Optimization For Non-Convex Problems via Column Generation
arXiv:1602.04409
Abstract
We apply column generation to approximating complex structured objects via a set of primitive structured objects under either the cross entropy or L2 loss. We use L1 regularization to encourage the use of few structured primitive objects. We attack approximation using convex optimization over an infinite number of variables each corresponding to a primitive structured object that are generated on demand by easy inference in the Lagrangian dual. We apply our approach to producing low rank approximations to large 3-way tensors.
References in corpus (17)
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Rejoinder to "Least angle regression" by Efron et al
- Least Angle Regression
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Discussion of "Least angle regression" by Efron et al
- Searching for Exotic Particles in High-Energy Physics with Deep Learning
- Detecting the community structure and activity patterns of temporal networks: a non-negative tensor factorization approach
- Tightening LP Relaxations for MAP using Message Passing
- A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorization
- Parallel Algorithms for Constrained Tensor Factorization via the Alternating Direction Method of Multipliers
- Barrier Frank-Wolfe for Marginal Inference
- Tracking Objects with Higher Order Interactions using Delayed Column Generation