Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces.
Yatin NandwaniDeepanshu Jindal MausamParag SinglaPublished in: ICLR (2021)
Keyphrases
- combinatorial problems
- neural learning
- structured output
- constraint programming
- metaheuristic
- constraint satisfaction problems
- traveling salesman problem
- combinatorial optimization
- constraint satisfaction
- phase transition
- multi layered
- maximum margin
- structured prediction
- latent variables
- global constraints
- branch and bound algorithm
- multiclass classification
- incremental learning
- neural network
- conditional random fields
- optimization problems
- discriminative learning
- genetic algorithm
- markov networks
- np complete
- information extraction