1.6k citations · 12.4k across the 394 of their papers we have counts for
9 papers · 2 filters
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
Raphael Suter, Đorđe Miladinović, Bernhard Schölkopf +1
The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use o…
Informative Features for Model Comparison
Wittawat Jitkrittum, Heishiro Kanagawa, Patsorn Sangkloy +3
Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models. We propose two new statistical tes…
Robustifying Independent Component Analysis by Adjusting for Group-Wise Stationary Noise
Niklas Pfister, Sebastian Weichwald, Peter Bühlmann +1
We introduce coroICA, confounding-robust independent component analysis, a novel ICA algorithm which decomposes linearly mixed multivariate observations into independent components…
A Local Information Criterion for Dynamical Systems
Arash Mehrjou, Friedrich Solowjow, Sebastian Trimpe +1
Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system.…
Deep Energy Estimator Networks
Saeed Saremi, Arash Mehrjou, Bernhard Schölkopf +1
Density estimation is a fundamental problem in statistical learning. This problem is especially challenging for complex high-dimensional data due to the curse of dimensionality. A…
Adversarial Extreme Multi-label Classification
Rohit Babbar, Bernhard Schölkopf
The goal in extreme multi-label classification is to learn a classifier which can assign a small subset of relevant labels to an instance from an extremely large set of target labe…