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 show its success on the high-dimensional data domains of ImageNet32x32, ImageNet128x128, CIFAR-10, and robotic hand trajectories, achieving significantly better samples than other likelihood models and on par with contemporary GAN approaches, while covering all modes of the data. We highlight unique capabilities of implicit generation, such as energy compositionality and corrupt image reconstruction and completion. Finally, we show that EBMs generalize well and are able to achieve state-of-the-art out-of-distribution classification, exhibit adversarially robust classification, coherent long term predicted trajectory roll-outs, and generate zero-shot compositions of models.
翻译:以能源为基础的模型(EBMs)具有吸引力,因为它们具有一般性和简单性,有可能建模,但历来难以培训。我们介绍了在连续神经网络上推广以MCMC为基础的电子BM培训的技术,并展示了其在图像Net32x32、图像Net128x128、CIFAR-10和机器人手轨等高维数据领域的成功,取得了比其他可能性模型更好的样本,与现代GAN方法相当,同时覆盖了所有数据模式。我们强调了隐含生成的独特能力,例如能源构成以及腐败的图像重建和完成。最后,我们表明EBMs非常普及,能够实现最先进的分配外分类、展示对抗性强的分类、连贯的长期预测轨迹推出,并产生零弹射模型构成。