Binary density ratio estimation (DRE), the problem of estimating the rat...
Manifold models consider natural-image patches to be on a low-dimensiona...
Multi-agent imitation learning aims to train multiple agents to perform ...
Blind pansharpening addresses the problem of generating a high
spatial-r...
This paper presents a quarter Laplacian filter that can preserve corners...
Weighted Gaussian Curvature is an important measurement for images. Howe...
We propose a novel theoretical framework to understand self-supervised
l...
Auto-regressive sequence generative models trained by Maximum Likelihood...
Offline reinforcement learning (RL) refers to the problem of learning
po...
Although Shannon theory states that it is asymptotically optimal to sepa...
Deep energy-based models (EBMs) are very flexible in distribution
parame...
Domain adaptation aims to leverage the supervision signal of source doma...
Providing a suitable reward function to reinforcement learning can be
di...
Reinforcement learning agents are prone to undesired behaviors due to re...
In this paper we study the convergence of generative adversarial network...
Green Security Games (GSGs) have been proposed and applied to optimize
p...
This paper aims to bring a new perspective for understanding GANs, by de...
Poaching continues to be a significant threat to the conservation of wil...
We propose Cooperative Training (CoT) for training generative models tha...
We conduct an empirical study on discovering the ordered collective dyna...
In this paper, we conduct an empirical study on discovering the ordered
...
As a new way of training generative models, Generative Adversarial Nets ...