The Gaussianity assumption has been consistently criticized as a main limitation of the V ariational Autoencoder (V AE) despite its efficiency in computational modeling. In this paper, we propose a new approach that expands the model capacity (i.e., expressive power of distributional family) without sacrificing the computational advantages of the V AE framework. Our V AE model's decoder is composed of an infinite mixture of asymmetric Laplace distribution, which possesses general

Different distribution shifts require different algorithmic and operational interventions. Methodological research must be grounded by the specific shifts they address.

Autoregressive and Masked Transformers are incredibly effective as generative models and classifiers.

However, this will lead to an intractable number of hyperparameters.

Meanwhile, the devised ensemble layer can be readily integrated into popular neuralarchitectures, including CNNs,RNNs,andGCNs.