The universal approximation property of width-bounded networks has been
...
An energy-based model (EBM) is a popular generative framework that offer...
Recent work has shown that automatic differentiation over the reals is a...
We study the problem of training a two-layer neural network (NN) of arbi...
In this paper, we propose a new covering technique localized for the
tra...
Randomized smoothing is currently a state-of-the-art method to construct...
It is known that Θ(N) parameters are sufficient for neural networks to
m...
Recent discoveries on neural network pruning reveal that, with a careful...
While semi-supervised learning (SSL) has proven to be a promising way fo...
The universal approximation property of width-bounded networks has been
...
In risk-sensitive learning, one aims to find a hypothesis that minimizes...
Magnitude-based pruning is one of the simplest methods for pruning neura...
Given a graphical model (GM), computing its partition function is the mo...
The Gibbs sampler is a particularly popular Markov chain used for learni...
Learning parameters of latent graphical models (GM) is inherently much h...
Max-product Belief Propagation (BP) is a popular message-passing algorit...
The max-product belief propagation (BP) is a popular message-passing
heu...