Search Results for author:
Found 28 papers, 7 papers with code
Independent Mechanism Analysis and the Manifold Hypothesis
As typical in ICA, previous work focused on the case with an equal number of latent components and observed mixtures.
Causal Component Analysis
As a corollary, this interventional perspective also leads to new identifiability results for nonlinear ICA -- a special case of CauCA with an empty graph -- requiring strictly fewer datasets than previous results.
Information Theoretic Measures of Causal Influences during Transient Neural Events
Transient phenomena play a key role in coordinating brain activity at multiple scales, however, their underlying mechanisms remain largely unknown.
Function Classes for Identifiable Nonlinear Independent Component Analysis
Several families of spurious solutions fitting perfectly the data, but that do not correspond to the ground truth factors can be constructed in generic settings.
Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions
How can agents learn internal models that veridically represent interactions with the real world is a largely open question.
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Leveraging self-consistency, we show that the ELBO converges to a regularized log-likelihood.
Bayesian Information Criterion for Event-based Multi-trial Ensemble data
Transient recurring phenomena are ubiquitous in many scientific fields like neuroscience and meteorology.
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
Model identifiability is a desirable property in the context of unsupervised representation learning.
Learning soft interventions in complex equilibrium systems
Complex systems often contain feedback loops that can be described as cyclic causal models.
Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations
A new perspective has been provided based on the principle of Independence of Causal Mechanisms (ICM), leading to the Spectral Independence Criterion (SIC), postulating that the power spectral density (PSD) of the cause time series is uncorrelated with the squared modulus of the frequency response of the filter generating the effect.
Exploring the Latent Space of Autoencoders with Interventional Assays
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods.
Independent mechanism analysis, a new concept?
Specifically, our approach is motivated by thinking of each source as independently influencing the mixing process.
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant.
Ranked #1 on
Image Classification
on Causal3DIdent
Assaying Large-scale Testing Models to Interpret COVID-19 Case Numbers
Large-scale testing is considered key to assess the state of the current COVID-19 pandemic.
Applications Populations and Evolution
Causal learning with sufficient statistics: an information bottleneck approach
Using these statistics we formulate new additional rules of causal orientation that provide causal information not obtainable from standard structure learning algorithms, which exploit only conditional independencies between observable variables.
Causal Feature Selection via Orthogonal Search
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.
Structure by Architecture: Structured Representations without Regularization
We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling.
A theory of independent mechanisms for extrapolation in generative models
Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments?
Tinkering with black boxes: counterfactuals uncover modularity in generative models
Deep generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are important tools to capture and investigate the properties of complex empirical data.
Orthogonal Structure Search for Efficient Causal Discovery from Observational Data
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.
Counterfactuals uncover the modular structure of deep generative models
Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data.
Coordinating users of shared facilities via data-driven predictive assistants and game theory
We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.
On the difference between building and extracting patterns: a causal analysis of deep generative models.
Generative models are important tools to capture and investigate the properties of complex empirical data.
Group invariance principles for causal generative models
The postulate of independence of cause and mechanism (ICM) has recently led to several new causal discovery algorithms.
Telling cause from effect in deterministic linear dynamical systems
Assuming the effect is generated by the cause trough a linear system, we propose a new approach based on the hypothesis that nature chooses the "cause" and the "mechanism that generates the effect from the cause" independent of each other.
Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators.
This framework enables us to develop an independence test between time series as well as a similarity measure to compare different types of coupling.
Towards a learning-theoretic analysis of spike-timing dependent plasticity
This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning.
