The paper introduces the Adversarially Learned Inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space, while the inference network maps training examples in the data space to the space of latent variables. An adversarial game is played between these two networks and a discriminative network trained to distinguish between joint latent/data-space samples from the generative network and joint samples from the inference network. The ALI model is designed to learn mutually coherent inference and generation networks, as demonstrated through model samples and reconstructions. The usefulness of the learned representations is confirmed by achieving competitive performance on the semi-supervised SVHN task. The paper also discusses the relationship between ALI and other generative models, such as VAEs and GANs, and provides experimental results on various datasets to validate the effectiveness of ALI.The paper introduces the Adversarially Learned Inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space, while the inference network maps training examples in the data space to the space of latent variables. An adversarial game is played between these two networks and a discriminative network trained to distinguish between joint latent/data-space samples from the generative network and joint samples from the inference network. The ALI model is designed to learn mutually coherent inference and generation networks, as demonstrated through model samples and reconstructions. The usefulness of the learned representations is confirmed by achieving competitive performance on the semi-supervised SVHN task. The paper also discusses the relationship between ALI and other generative models, such as VAEs and GANs, and provides experimental results on various datasets to validate the effectiveness of ALI.