We study causal representation learning, the task of inferring latent ca...
Independent Component Analysis (ICA) aims to recover independent latent
...
Transient phenomena play a key role in coordinating brain activity at
mu...
Unsupervised learning of latent variable models (LVMs) is widely used to...
How can we acquire world models that veridically represent the outside w...
Variational autoencoders (VAEs) are a popular framework for modeling com...
Transient recurring phenomena are ubiquitous in many scientific fields l...
Model identifiability is a desirable property in the context of unsuperv...
Complex systems often contain feedback loops that can be described as cy...
Distinguishing between cause and effect using time series observational ...
Independent component analysis provides a principled framework for
unsup...
Self-supervised representation learning has shown remarkable success in ...
Large-scale testing is considered key to assessing the state of the curr...
The inference of causal relationships using observational data from part...
The problem of inferring the direct causal parents of a response variabl...
Time series datasets often contain heterogeneous signals, composed of bo...
Deep generative models reproduce complex empirical data but cannot
extra...
The problem of inferring the direct causal parents of a response variabl...
Deep generative models such as Generative Adversarial Networks (GANs) an...
We study machine learning-based assistants that support coordination bet...
The postulate of independence of cause and mechanism (ICM) has recently ...
Inferring a cause from its effect using observed time series data is a m...
This paper suggests a learning-theoretic perspective on how synaptic
pla...