Implicit Generation and Generalization in Energy-Based 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.
Code (4)
Tasks
General ClassificationImage ReconstructionRobust classificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The energy landscape of a simple neural network
We explore the energy landscape of a simple neural network. In particular, we expand upon previous work demonstrating that the empirical complexity of fitted neural networks is vastly less than a naive parameter count wo…
Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice
We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially co…
regressionPlanning with Sequence Models through Iterative Energy Minimization
Recent works have shown that sequence modeling can be effectively used to train reinforcement learning (RL) policies. However, the success of applying existing sequence models to planning, in which we wish to obtain a tr…
Language ModelingLanguage ModellingReinforcement Learning (RL)Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limited adaptability to learn graph metrics, e…
Generalization BoundsGraph ClassificationGraph LearningImplicit Generation and Modeling with Energy Based 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…
General ClassificationImage GenerationImage ReconstructionRobust classification