Search Results for author:
Found 3 papers, 0 papers with code
Constructive universal distribution generation through deep ReLU networks
We present an explicit deep network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional target distribution of finite differential entropy and Lipschitz-continuous pdf.
The Hazards and Benefits of Condescension in Social Learning
In a misspecified social learning setting, agents are condescending if they perceive their peers as having private information that is of lower quality than it is in reality.
Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
We present an explicit deep neural network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional Lipschitz-continuous target distribution.
