Learning from Conditional Distributions via Dual Embeddings

AISTATS, pp. 1458-1467, 2017.

Cited by: 56|Views121
EI

Abstract:

Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is associated with a conditional distribution $p(z|x)$ represented by samples ${z_i}_{i=1}^M$, and the goal is ...More

Code:

Data:

Your rating :
0

 

Tags
Comments