57 citations · 106 across the 9 of their papers we have counts for
3 papers · 1 filter
Causality can systematically address the monsters under the bench(marks)
Felix Leeb, Zhijing Jin, Bernhard Schölkopf
Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever mo…
Exploring the Latent Space of Autoencoders with Interventional Assays
Felix Leeb, Stefan Bauer, Michel Besserve +1
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without…
Structure by Architecture: Structured Representations without Regularization
Felix Leeb, Guilia Lanzillotta, Yashas Annadani +3
We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on ma…