Search Results for author:
Found 16 papers, 11 papers with code
Interaction Asymmetry: A General Principle for Learning Composable Abstractions
Using this formalism, we prove that interaction asymmetry enables both disentanglement and compositional generalization.
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "easy" and "easiest" being parallel to that between "lucky" and "luckiest".
Causal Representation Learning in Temporal Data via Single-Parent Decoding
From these, one needs to learn both a mapping to causally-relevant latent variables, such as a high-level representation of the El Ni\~no phenomenon and other processes, as well as the causal model over them.
Sparsity regularization via tree-structured environments for disentangled representations
The key insight is that the mapping from latent variables driven by gene expression to the phenotype of interest changes sparsely across closely related environments.
A Sparsity Principle for Partially Observable Causal Representation Learning
Causal representation learning aims at identifying high-level causal variables from perceptual data.
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
We develop a nonparametric identifiability theory that formalizes this principle and shows that the latent factors can be recovered by regularizing the learned causal graph to be sparse.
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities.
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited.
Partial Disentanglement via Mechanism Sparsity
In this work, we introduce a generalization of this theory which applies to any ground-truth graph and specifies qualitatively how disentangled the learned representation is expected to be, via a new equivalence relation over models we call consistency.
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent factors of interest depend sparsely on past latent factors and/or observed auxiliary variables.
On the Convergence of Continuous Constrained Optimization for Structure Learning
Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity.
Differentiable Causal Discovery from Interventional Data
This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interventional data.
Gradient-Based Neural DAG Learning
We propose a novel score-based approach to learning a directed acyclic graph (DAG) from observational data.
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
We show that causal structures can be parameterized via continuous variables and learned end-to-end.
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
We formulate the problem as a two-stage optimal prediction stochastic program whose solution we predict with a supervised machine learning algorithm.
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
We aim to predict at a high speed the expected TDOS associated with the second stage problem, conditionally on the first stage variables.
