Summary: A framework for learning complex structured output representations is presented. To this end variational auto-encoders (VAE) are extended to conditional VAEs,' i.e., conditioned on the input data x. Quality - The paper is mostly well written, could however be improved occasionally. Clarity - The idea is clearly presented but some details are missing. Originality - Conditional VAEs seem to be a straightforward extension of standard VAEs, but certainly worth a discussion Significance - The significance could be improved by a more extensive evaluation showing results for various modifications Comments: - I think the term generative is typically used when learning distributions that also involve the input data.

This paper introduces a new technique to measure the feature dependency of neural network models. The motivation is to better understand a model by querying whether it is using information from human-understandable features, e.g., anatomical shape, volume, or image texture. Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance. A targeted feature is "removed" by collapsing the dimension in the data distribution that corresponds to that feature. We perform this by moving data points along the feature dimension to a baseline feature value while staying on the data manifold, as estimated by a deep generative model. Then we observe how the model's performance changes on the modified test data set, with the target feature dimension removed. We test our method on deep neural network models trained on synthetic image data with known ground truth, an Alzheimer's disease prediction task using MRI and hippocampus segmentations from the OASIS-3 dataset, and a cell nuclei classification task using the Lizard dataset.

We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety of image classification and generation tasks. Our framework is based on the Variational Autoencoder architecture and uses a novel approach for augmentation via linear transformation within the latent space itself. We explore losses and augmentation latent geometry to enforce the transformations to be composable and involuntary, thus allowing the transformations to be readily combined or inverted. Finally, we show these properties are better performing with certain pairs of augmentations, but we can transfer the latent space to other sets of augmentations to modify performance, effectively constraining the VAE's bottleneck to preserve the variance of specific augmentations and features of the image which we care about. We demonstrate the effectiveness of our approach with initial results on the MNIST dataset against both a standard VAE and a Conditional VAE. This latent augmentation method allows for much greater control and geometric interpretability of the latent space, making it a valuable tool for researchers and practitioners in the field.

Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional trajectory representation model, a conditional variational dynamics model to predict the expected representation of future trajectory and a convex trajectory return model that maps a trajectory representation to its return. Our algorithm is evaluated in MuJoCo continuous control tasks and shows superior results under both common settings and delayed reward settings.