Autoregressive models (ARMs) currently hold state-of-the-art performance in
likelihood-based modeling of image and audio data. Generally, neural network
based ARMs are designed to allow fast inference, but sampling from these models
is impractically slow. In this paper, we introduce the predictive sampling
algorithm: a procedure that exploits the fast inference property of ARMs in
order to speed up sampling, while keeping the model intact. We propose two
variations of predictive sampling, namely sampling with ARM fixed-point
iteration and learned forecasting modules. Their effectiveness is demonstrated
in two settings: i) explicit likelihood modeling on binary MNIST, SVHN and
CIFAR10, and ii) discrete latent modeling in an autoencoder trained on SVHN,
CIFAR10 and Imagenet32. Empirically, we show considerable improvements over
baselines in number of ARM inference calls and sampling speed.

本论文提出了一种预测采样算法，利用 ARMs 的快速推断能力加速采样，证明其在二元 MNIST 等设置下可显著提高推断调用次数和采样速度。

基于预测自回归模型的预测采样

Predictive Sampling with Forecasting Autoregressive Models

Energy based models (EBMs) are appealing due to their generality and
simplicity in likelihood modeling, but have been traditionally difficult to
train. We present techniques to scale MCMC based EBM training on continuous
neural networks, and we show its success on the high-dimensional data domains
of ImageNet32x32, ImageNet128x128, CIFAR-10, and robotic hand trajectories,
achieving better samples than other likelihood models and nearing the
performance of contemporary GAN approaches, while covering all modes of the
data. We highlight some unique capabilities of implicit generation such as
compositionality and corrupt image reconstruction and inpainting. Finally, we
show that EBMs are useful models across a wide variety of tasks, achieving
state-of-the-art out-of-distribution classification, adversarially robust
classification, state-of-the-art continual online class learning, and coherent
long term predicted trajectory rollouts.

本文介绍了一些在连续神经网络上训练 MCMC 的能量基础模型的技术，在许多高维度数据域上，如 ImageNet 和 CIFAR-10, 它们的样本表现优于其他可能性模型，并接近当代生成对抗网络 GAN 的表现，同时覆盖所有数据模态。此外，作者还阐述了基于 EBM 的独特能力，如组合性和损坏图像的重建和修复，最后证明 EBMs 模型是跨多种任务有用的模型，进而实现了最先进的超出分布分类、对抗性稳健分类、在线连续类学习和连续长期预测轨迹