Corpus ID: 16372888

9 Entropy Regularization

@inproceedings{Yoshua9ER,
  title={9 Entropy Regularization},
  author={Yves Grandvalet Yoshua}
}
The problem of semi-supervised induction consists in learning a decision rule from labeled and unlabeled data. This task can be undertaken by discriminative methods, provided that learning criteria are adapted consequently. In this chapter, we motivate the use of entropy regularization as a means to benefit from unlabeled data in the framework of maximum a posteriori estimation. The learning criterion is derived from clearly stated assumptions and can be applied to any smoothly parametrized… Expand

Figures and Tables from this paper

Categorical Reparameterization with Gumbel-Softmax
Adversarial Bootstrapping for Dialogue Model Training

References

SHOWING 1-10 OF 67 REFERENCES
Restricted Bayes Optimal Classifiers
Information Regularization with Partially Labeled Data
Semi Supervised Logistic Regression
Beyond the point cloud: from transductive to semi-supervised learning
Learning with Local and Global Consistency
Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions
Structure Learning in Conditional Probability Models via an Entropic Prior and Parameter Extinction
  • M. Brand
  • Mathematics, Computer Science
  • Neural Computation
  • 1999
...
1
2
3
4
5
...