… In this paper, we study how to model convex gradients by … network, which we call the Input
Convex Gradient Network (… to taking the gradient of an Input-Convex Neural Network (ICNN), …

… The networks allow for efficient inference via optimization over some inputs to the network
… We show that many existing neural network architectures can be made inputconvex with a …

… • Optimize the output weights using a convex optimizer. • In case (b), tune both input and
output weights by conjugate gradient descent on C and finally re-optimize the output weights …

… This involves learning two convex functions, by … field of input convex neural networks, we
propose a new framework to estimate the optimal transport mapping as the gradient of a convex …

… , input convexity … is that input convex neural networks have limited representation power.
Future work will include increasing the representation power of input convex neural networks …

… surrogate model of the distribution system that is guaranteed to be convex … network an input
convex neural network (ICNN) [24], [25], which is constructed using common neural network …

… method for computing Wasserstein gradient flows. Key to our approach is the parameterization
of the space of convex functions with Input Convex Neural Networks. We showed that JKO…

… We also include non-convex networks in these experiments to illustrate that ICNNs with our
… as well as regular networks. However, we would like to stress that non-convex networks are …

… using gradient descent, despite the worst case hardness of the underlying non-convex op…
, but that when the input distribution is Gaussian, gradient descent converges to the global …

… high penetration of renewables in power distribution networks. A promising approach is to
… convexity results of voltage regulation problem, we design an input convex neural network …