Learning from Conditional Distributions via Dual Kernel Embeddings
arXiv: Learning, Volume abs/1607.04579, 2016.
In many machine learning problems, such as policy evaluation in reinforcement learning and learning with invariance, each data point $x$ itself is a conditional distribution $p(z|x)$, and we want to learn a function $f$ which links these conditional distributions to target values $y$. The learning problem becomes very challenging when we ...More
PPT (Upload PPT)