70 citations · 221 across the 18 of their papers we have counts for
18 papers
CLadder: Assessing Causal Reasoning in Language Models
Zhijing Jin, Yuen Chen, Felix Leeb +8
The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason…
Independent Mechanism Analysis and the Manifold Hypothesis
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Independent Mechanism Analysis (IMA) seeks to address non-identifiability in nonlinear Independent Component Analysis (ICA) by assuming that the Jacobian of the mixing function has…
Nonparametric Identifiability of Causal Representations from Unknown Interventions
Julius von Kügelgen, Michel Besserve, Liang Wendong +5
We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional mixtures of the variables. Prior work relies…
Causal Component Analysis
Liang Wendong, Armin Kekić, Julius von Kügelgen +4
Independent Component Analysis (ICA) aims to recover independent latent variables from observed mixtures thereof. Causal Representation Learning (CRL) aims instead to infer causall…
Probing the Robustness of Independent Mechanism Analysis for Representation Learning
Joanna Sliwa, Shubhangi Ghosh, Vincent Stimper +2
One aim of representation learning is to recover the original latent code that generated the data, a task which requires additional information or inductive biases. A recently prop…
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Patrik Reizinger, Luigi Gresele, Jack Brady +6
Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidenc…
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable…
Causal Inference Through the Structural Causal Marginal Problem
Luigi Gresele, Julius von Kügelgen, Jonas M. Kübler +3
We introduce an approach to counterfactual inference based on merging information from multiple datasets. We consider a causal reformulation of the statistical marginal problem: gi…
Independent mechanism analysis, a new concept?
Luigi Gresele, Julius von Kügelgen, Vincent Stimper +2
Independent component analysis provides a principled framework for unsupervised representation learning, with solid theory on the identifiability of the latent code that generated…
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
Julius von Kügelgen, Yash Sharma, Luigi Gresele +4
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations inte…
Learning explanations that are hard to vary
Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto +2
In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a…
Relative gradient optimization of the Jacobian term in unsupervised deep learning
Luigi Gresele, Giancarlo Fissore, Adrián Javaloy +2
Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. A popular approach for solving it is mapping the observations in…
Modeling Shared Responses in Neuroimaging Studies through MultiView ICA
Hugo Richard, Luigi Gresele, Aapo Hyvärinen +3
Group studies involving large cohorts of subjects are important to draw general conclusions about brain functional organization. However, the aggregation of data coming from multip…
Simpson's paradox in Covid-19 case fatality rates: a mediation analysis of age-related causal effects
Julius von Kügelgen, Luigi Gresele, Bernhard Schölkopf
We point out an instantiation of Simpson's paradox in Covid-19 case fatality rates (CFRs): comparing a large-scale study from China (17 Feb) with early reports from Italy (9 Mar),…
Privacy-Preserving Causal Inference via Inverse Probability Weighting
Si Kai Lee, Luigi Gresele, Mijung Park +1
The use of inverse probability weighting (IPW) methods to estimate the causal effect of treatments from observational studies is widespread in econometrics, medicine and social sci…
The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA
Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou +2
We consider the problem of recovering a common latent source with independent components from multiple views. This applies to settings in which a variable is measured with multiple…
Orthogonal Structure Search for Efficient Causal Discovery from Observational Data
Anant Raj, Luigi Gresele, Michel Besserve +2
The problem of inferring the direct causal parents of a response variable among a large set of explanatory variables is of high practical importance in many disciplines. Recent wor…
On Maximum Entropy and Inference
Luigi Gresele, Matteo Marsili
Maximum Entropy is a powerful concept that entails a sharp separation between relevant and irrelevant variables. It is typically invoked in inference, once an assumption is made on…