Goto

Collaborating Authors

 Europe




Joint distribution optimal transportation for domain adaptation

Neural Information Processing Systems

However, the generating process can be different in several aspects, such as the conditions and devices used for acquisition, different pre-processing, different compressions, etc. Domain adaptation





A Locally Adaptive Normal Distribution

Neural Information Processing Systems

The underlyingmetricis,however,non-parametric.Wedevelopamaximumlikelihood algorithm to infer the distribution parameters that relies on a combination of gradient descent and Monte Carlo integration. We further extend the LAND to mixture models, andprovidethecorresponding EMalgorithm.