Mario Lucic

TL;DR: The authors show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data, and suggest that future work on disentanglement learning should be explicit about the role of inductive bias and (implicit) supervision.

TL;DR: This paper conducted a large-scale empirical study on state-of-the-art GAN models and evaluation measures and found that most models can reach similar scores with enough hyperparameter optimization and random restarts, and that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes.

TL;DR: This article conducted a large-scale empirical study on state-of-the-art GAN models and evaluation measures and found that most models can reach similar scores with enough hyperparameter optimization and random restarts, and that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes.

TL;DR: This work shows the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain, and shows that this problem appears in a wide variety of practical ML pipelines.

TL;DR: An in-depth review of recent advances in representation learning with a focus on autoencoder-based models and makes use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features.