Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

90180269359 · Jun 202019922001200920172026
48 results for Representation Intervention

Interventional data helps identify latent factors without distributional assumptions.

problem Identifying latent factors from interventional data without distributional assumptions.
method Leveraging geometric signatures of latent factors' support from interventional data.
result Latent causal factors can be identified up to permutation and scaling given data from perfect do-interventions.

Paper tackles intervention extrapolation using identifiable representations.

problem Predicting effects of unseen interventions on outcomes.
method Combines identifiable representation learning with autoencoders to enforce linear invariance.
result Identifiable representations enable non-linear extrapolation of interventions.

This paper tackles CRL for multi-node interventions, achieving identifiability guarantees.

problem CRL under unknown multi-node interventions, focusing on single-node assumptions.
method Establishes identifiability results for general latent causal models under stochastic interventions.
result Identifiability up to ancestors using soft interventions, perfect identifiability using hard interventions.

The paper shows how to learn causal representations with few environments and finite samples.

problem Learning causal representations from limited data and environments.
method Explicit, finite-sample guarantees with a logarithmic number of interventions.
result Consistent recovery of latent causal graph, mixing matrix, and unknown intervention targets.

Introduces CStrees for modeling context-specific causal models from observational and interventional data.

problem Modeling context-specific causal relationships from mixed data types.
method Introduces CStrees with a novel factorization criterion and graphical characterization for context-specific conditional independence models.
result Derives a graphical characterization of model equivalence for observational CStrees and extends it to CStree models under context-specific interventions.

New method identifies causal variables from multi-node interventions, expanding on previous single-node approaches.

problem Inferring high-level causal variables from low-level observations under multiple interventions.
method Exploits variance trace of ground truth causal variables and regularizes for sparsity.
result First identifiability result for causal representation learning with multiple node interventions.

Study identifies causal relationships without direct supervision from unknown interventions.

problem Identify causal relationships from unknown interventions without direct supervision.
method General nonparametric setting with multiple datasets from unknown interventions.
result Identify ground truth latents and causal graph up to ambiguities.

COCA refactors training data to identify and erase unsafe concepts in LLMs.

problem Identifying and erasing unsafe concepts in Large Language Models (LLMs) for safety alignment.
method Concept Concentration (COCA) refactors training data with an explicit reasoning process to identify and erase unsafe concepts.
result COCA significantly reduces both in-distribution and out-of-distribution jailbreak success rates while maintaining strong performance on regular tasks.

Paper establishes identifiability and achievability for causal representation learning.

problem Identifying and recovering latent causal models and variables from observational and interventional data.
method Establishes identifiability and achievability using uncoupled interventions and a recovery algorithm.
result Guaranteed perfect recovery of latent causal model and variables under uncoupled interventions.

New method identifies causal relationships from interventions in complex systems.

problem Learning causal representations from unknown, latent interventions with general nonlinear mixing.
method Strong identifiability results with unknown single-node interventions, using geometric structure of transformed data.
result First instance of causal identifiability from non-paired interventions for deep neural network embeddings.

Paper recovers latent causal structure and linear transformation from indirect observations.

problem Recovering latent causal structure and linear transformation from indirect observations.
method Established sufficient conditions for DAG recovery, leveraged score function properties, and used soft/hard interventions.
result Perfect recovery of latent DAG structure and linear transformation up to scaling using soft interventions, hard interventions with additional hypothesis testing.

The paper tackles causal disentanglement with linear models and interventions.

problem Identify latent variables in a causal model from observed data.
method Use linear transformations and interventions to uniquely identify latent variables.
result A single intervention on each latent variable is sufficient for identifying the latent causal model.

The paper tackles generalization in machine learning by finding invariant representations of data.

problem Obtaining robust models that generalize well across different training environments.
method The paper introduces the concept of εε-approximate invariance to study the robustness of models to unseen SEMs.
result The paper provides finite-sample out-of-distribution generalization guarantees for approximate invariance in linear SEMs.

FMI uses matching to mimic interventions for causal feature learning.

problem Challenges in causal discovery from observational data.
method Feature Matching Intervention (FMI) using matching to emulate perfect interventions.
result FMI outperforms in identifying causal features from observational data.

This paper tackles causal representation learning with linear and general transformations.

problem Identify and recover latent causal variables and graphs under unknown transformations.
method Score-based algorithms that use gradients of log-density functions for identifiability and achievability.
result Two stochastic hard interventions per node are sufficient for identifiability of general transformations.

Causal Bayesian networks interpret actions as interventions to connect models to real-world outcomes.

problem Connecting causal model predictions to real-world outcomes.
method Formal framework to interpret actions as interventions and prove impossibility results.
result No non-circular interpretation exists that satisfies natural desiderata without violating some.

A model learns causal representations from high-dimensional data.

problem Challenges in learning causal representations from high-dimensional data.
method Formulated a latent variable decoder model, Decoder BCD, for Bayesian causal discovery.
result Shows that using known intervention targets as labels helps in unsupervised Bayesian inference over structure and parameters.

Empirical Bayes improves causal representation learning across multiple domains.

problem Estimating causal representations from data across multiple domains.
method Developed an EB ff-modeling algorithm for linearly-mixed causal representations.
result Our method achieves more accurate estimation of causal variables than other methods.

NCoRE learns counterfactual representations for combined treatments.

problem Estimating individual response to multiple simultaneous interventions.
method Neural conditional representation with modulators for cross-treatment interactions.
result NCoRE significantly outperforms existing methods in counterfactual treatment effect estimation.

This research tackles intervention-centric causal reasoning in learning agents by using meta-learning.

problem Learning agents lack the concept of interventions, making causal learning challenging.
method A meta-reinforcement learning algorithm is used to learn causal relationships from observational data.
result The approach enables agents to learn and manipulate the environment effectively.

Paper characterizes causal graphs from hard interventions and proposes a learning algorithm.

problem Discovering causal structure from hard interventions and observational data.
method Proposes graphical constraints and a learning algorithm based on do-calculus.
result Characterizes interventional equivalence classes of causal graphs with latent variables.

COTA learns abstraction maps from data without complete SCM knowledge.

problem Learning causally consistent representations at different resolutions.
method Multi-marginal Optimal Transport (OT) with do-calculus constraints and interventional cost.
result COTA outperforms non-causal and independent formulations on synthetic and real-world problems.

Develops methods to create consistent surrogate models for agent-based simulators.

problem High computational costs and misjudgment of interventions in agent-based models.
method Causal abstractions to learn interventionally consistent surrogate models.
result Surrogates trained for interventional consistency closely mimic the agent-based model's behavior under interventions.

Localized Multidirectional Correction improves non-refusal target-response behavior in foundation models.

problem Controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models.
method Introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework.
result Substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.

This paper tackles causal representation learning from multiple distributions without hard interventions.

problem Recovering latent causal variables and their relations from multiple distributions.
method Develops general solutions for causal representation learning without hard interventions, under sparsity constraints and suitable change conditions.
result Recovering the moralized graph of the underlying directed acyclic graph and latent variables related to the underlying causal model.

New method identifies stable latent variables across different domains using weak distributional invariances.

problem Learning causal representations for multi-domain datasets.
method Autoencoders incorporating weak distributional invariances.
result Autoencoders can identify stable latent variables across different domains.

New method recovers causal DAGs from general environments without strict assumptions.

problem Recovering causal DAGs from real-world data with varying distributions.
method Formalizes desiderata for causal representation learning in general environments, leveraging sufficient change conditions up to third-order derivatives.
result Fully recovers latent DAG and identifies latent variables up to minor indeterminacies under nonparametric mixing.

PLIs improve classifier performance by fine-tuning latent representations.

problem Difficult interpretation of high-dimensional latent representations in neural networks.
method Back-propagation of manual changes to low-dimensional embeddings using t-distributed stochastic neighbourhood embeddings.
result Manual separation of class clusters in latent space enhances classifier performance.

Unified multilinear model for causal factor disentanglement.

problem Disentangling causal factors from complex data without direct manipulation.
method Hierarchical block multilinear factorization (M-mode Block SVD) and incremental approach.
result Interpretable object representation robust to occlusion and reduced training data.

New method identifies latent variables with causal dependencies from observed data.

problem Identify latent variables with causal relationships from observed data.
method Linear causal disentanglement via higher-order cumulants, with perfect and soft interventions.
result Recovery of parameters via coupled tensor decomposition and polynomial equations.

Framework learns interpretable concepts from data without interventions.

problem Learning spurious correlations between concepts in CBMs.
method Causal representation learning (CRL) to align latent variables with interpretable concepts using few labels.
result Framework provides theoretical guarantees on correctness and number of required labels without interventions.

New method identifies causal relationships without strong assumptions.

problem Causal Representation Learning (CRL) is ill-posed due to representation and causal discovery issues.
method Identifiability based on grouping of observational variables, self-supervised estimation framework.
result Practical identifiability conditions without temporal structure, interventions, or weak supervision.

We identify which latent factors change between environments in linear causal models.

problem Identify latent factors that change between environments in linear causal models with fewer than dd interventions.
method Propose a method to identify shifted nodes in a smaller number of environments with coarser interventions.
result It is possible to identify the set of shifted nodes under mild assumptions.

DCM uses diffusion models to answer causal queries from observational data.

problem Answering causal queries from observational data alone.
method Diffusion models to learn causal mechanisms and generate latent encodings.
result Significant improvements over existing methods for causal query answering.

Bayesian approach learns causal concepts from diverse social surveys.

problem Inferring causal concepts from heterogeneous data with sparse changes.
method Hierarchical Bayesian model with sequential Monte Carlo sampling.
result Model infers meaningful causal concepts and plausible relations.

ReCoRe learns invariant features for world navigation using contrastive learning and regularizers.

problem Limited sample efficiency and overfitting to training scenarios in RL for visual navigation.
method Contrastive unsupervised learning and intervention-invariant regularizer.
result Significantly improves sample efficiency and generalization in out-of-distribution point navigation tasks.

Estimates joint causal effects using single-variable interventions on nonlinear models.

problem Estimating joint causal effects from single-variable interventions.
method Identifiability result and practical estimator for decomposing causal effects.
result Joint effects can be inferred without joint interventional data for nonlinear additive models.

Study identifies latent variables and causal relationships from multiple environments.

problem Identify latent variables and causal relationships from multiple environments.
method Proposes algorithm LiNGCReL for identifying causal graph up to surrounded-node ambiguity.
result Identifies latent variables up to surrounded-node ambiguity (SNA) in linear causal models.