Search Results for author: Elias Bareinboim

Found 37 papers, 5 papers with code

Efficient Identification in Linear Structural Causal Models with Auxiliary Cutsets

no code implementations ICML 2020 Daniel Kumor, Carlos Cinelli, Elias Bareinboim

We develop a a new polynomial-time algorithm for identification in linear Structural Causal Models that subsumes previous non-exponential identification methods when applied to direct effects, and unifies several disparate approaches to identification in linear systems.

Causal Effect Identifiability under Partial-Observability

no code implementations ICML 2020 Sanghack Lee, Elias Bareinboim

Finally, building on these graphical properties, we develop an algorithm that returns a formula for a causal effect in terms of the available distributions.

Finding and Listing Front-door Adjustment Sets

1 code implementation11 Oct 2022 Hyunchai Jeong, Jin Tian, Elias Bareinboim

Identifying the effects of new interventions from data is a significant challenge found across a wide range of the empirical sciences.

Neural Causal Models for Counterfactual Identification and Estimation

no code implementations30 Sep 2022 Kevin Xia, Yushu Pan, Elias Bareinboim

We show that this algorithm is sound and complete for deciding counterfactual identification in general settings.

Fairness

Sequential Causal Imitation Learning with Unobserved Confounders

no code implementations NeurIPS 2021 Daniel Kumor, Junzhe Zhang, Elias Bareinboim

"Monkey see monkey do" is an age-old adage, referring to na\"ive imitation without a deep understanding of a system's underlying mechanics.

Imitation Learning

Causal Fairness Analysis

no code implementations23 Jul 2022 Drago Plecko, Elias Bareinboim

The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms that generate the disparity in the first place, challenge we call the Fundamental Problem of Causal Fairness Analysis (FPCFA).

Decision Making Fairness

Effect Identification in Cluster Causal Diagrams

no code implementations22 Feb 2022 Tara V. Anand, Adèle H. Ribeiro, Jin Tian, Elias Bareinboim

In this paper, we introduce a new type of graphical model called cluster causal diagrams (for short, C-DAGs) that allows for the partial specification of relationships among variables based on limited prior knowledge, alleviating the stringent requirement of specifying a full causal diagram.

Double Machine Learning Density Estimation for Local Treatment Effects with Instruments

no code implementations NeurIPS 2021 Yonghan Jung, Jin Tian, Elias Bareinboim

We study the problem of estimating the density of the causal effect of a binary treatment on a continuous outcome given a binary instrumental variable in the presence of covariates.

BIG-bench Machine Learning Density Estimation

Causal Identification with Matrix Equations

no code implementations NeurIPS 2021 Sanghack Lee, Elias Bareinboim

Causal effect identification is concerned with determining whether a causal effect is computable from a combination of qualitative assumptions about the underlying system (e. g., a causal graph) and distributions collected from this system.

Causal Identification

Partial Counterfactual Identification from Observational and Experimental Data

no code implementations12 Oct 2021 Junzhe Zhang, Jin Tian, Elias Bareinboim

This paper investigates the problem of bounding counterfactual queries from an arbitrary collection of observational and experimental distributions and qualitative knowledge about the underlying data-generating model represented in the form of a causal diagram.

Nested Counterfactual Identification from Arbitrary Surrogate Experiments

no code implementations NeurIPS 2021 Juan D Correa, Sanghack Lee, Elias Bareinboim

In this paper, we study the identification of nested counterfactuals from an arbitrary combination of observations and experiments.

Fairness

The Causal-Neural Connection: Expressiveness, Learnability, and Inference

2 code implementations NeurIPS 2021 Kevin Xia, Kai-Zhan Lee, Yoshua Bengio, Elias Bareinboim

Given this property, one may be tempted to surmise that a collection of neural nets is capable of learning any SCM by training on data generated by that SCM.

Causal Identification Causal Inference +1

Partial Identification of Counterfactual Distributions

no code implementations NeurIPS 2021 Junzhe Zhang, Elias Bareinboim, Jin Tian

We show that all counterfactual distributions (over finite observed variables) in an arbitrary causal diagram could be generated by a special family of structural causal models (SCMs), compatible with the same causal diagram, where unobserved (exogenous) variables are discrete, taking values in a finite domain.

Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning

no code implementations NeurIPS 2020 Amin Jaber, Murat Kocaoglu, Karthikeyan Shanmugam, Elias Bareinboim

One fundamental problem in the empirical sciences is of reconstructing the causal structure that underlies a phenomenon of interest through observation and experimentation.

Causal Discovery

Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe

no code implementations NeurIPS 2020 Sanghack Lee, Elias Bareinboim

Intelligent agents are continuously faced with the challenge of optimizing a policy based on what they can observe (see) and which actions they can take (do) in the environment where they are deployed.

Learning Causal Effects via Weighted Empirical Risk Minimization

no code implementations NeurIPS 2020 Yonghan Jung, Jin Tian, Elias Bareinboim

In this paper, we develop a learning framework that marries two families of methods, benefiting from the generality of the causal identification theory and the effectiveness of the estimators produced based on the principle of ERM.

Causal Identification Causal Inference

General Transportability of Soft Interventions: Completeness Results

no code implementations NeurIPS 2020 Juan Correa, Elias Bareinboim

As a corollary, we show that the $\sigma$-calculus is complete for the task of soft-transportability.

Causal Inference

Causal Inference and Data Fusion in Econometrics

no code implementations19 Dec 2019 Paul Hünermund, Elias Bareinboim

Learning about cause and effect is arguably the main goal in applied econometrics.

Econometrics

Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes

no code implementations NeurIPS 2019 Junzhe Zhang, Elias Bareinboim

A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments and covariates' history.

Decision Making reinforcement-learning +1

Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions

no code implementations NeurIPS 2019 Murat Kocaoglu, Amin Jaber, Karthikeyan Shanmugam, Elias Bareinboim

We introduce a novel notion of interventional equivalence class of causal graphs with latent variables based on these invariances, which associates each graphical structure with a set of interventional distributions that respect the do-calculus rules.

Identification of Conditional Causal Effects under Markov Equivalence

no code implementations NeurIPS 2019 Amin Jaber, Jiji Zhang, Elias Bareinboim

A generalization of this problem restricts the qualitative knowledge to a class of Markov equivalent causal diagrams, which, unlike a single, fully-specified causal diagram, can be inferred from the observational distribution.

Causal Identification

Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets

1 code implementation NeurIPS 2019 Daniel Kumor, Bryant Chen, Elias Bareinboim

Building on the literature of instrumental variables (IVs), a plethora of methods has been developed to identify causal effects in linear systems.

Causal Identification under Markov Equivalence

no code implementations15 Dec 2018 Amin Jaber, Jiji Zhang, Elias Bareinboim

The problem of identification of causal effects is concerned with determining whether a causal effect can be computed from a combination of observational data and substantive knowledge about the domain under investigation, which is formally expressed in the form of a causal graph.

Causal Identification

Structural Causal Bandits: Where to Intervene?

1 code implementation NeurIPS 2018 Sanghack Lee, Elias Bareinboim

We study the problem of identifying the best action in a sequential decision-making setting when the reward distributions of the arms exhibit a non-trivial dependence structure, which is governed by the underlying causal model of the domain where the agent is deployed.

Decision Making

Equality of Opportunity in Classification: A Causal Approach

no code implementations NeurIPS 2018 Junzhe Zhang, Elias Bareinboim

The goal of this paper is to develop a principled approach to connect the statistical disparities characterized by the EO and the underlying, elusive, and frequently unobserved, causal mechanisms that generated such inequality.

Classification Fairness +1

Experimental Design for Learning Causal Graphs with Latent Variables

no code implementations NeurIPS 2017 Murat Kocaoglu, Karthikeyan Shanmugam, Elias Bareinboim

Next, we propose an algorithm that uses only O(d^2 log n) interventions that can learn the latents between both non-adjacent and adjacent variables.

Experimental Design

Budgeted Experiment Design for Causal Structure Learning

no code implementations ICML 2018 AmirEmad Ghassami, Saber Salehkaleybar, Negar Kiyavash, Elias Bareinboim

We study the problem of causal structure learning when the experimenter is limited to perform at most $k$ non-adaptive experiments of size $1$.

Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables

no code implementations ICML 2017 Bryant Chen, Daniel Kumor, Elias Bareinboim

In this paper, we provide an algorithm for the identification of causal parameters in linear structural models that subsumes previous state-of-the-art methods.

Counterfactual Data-Fusion for Online Reinforcement Learners

no code implementations ICML 2017 Andrew Forney, Judea Pearl, Elias Bareinboim

The Multi-Armed Bandit problem with Unobserved Confounders (MABUC) considers decision-making settings where unmeasured variables can influence both the agent’s decisions and received rewards (Bareinboim et al., 2015).

Decision Making Thompson Sampling

Bandits with Unobserved Confounders: A Causal Approach

no code implementations NeurIPS 2015 Elias Bareinboim, Andrew Forney, Judea Pearl

The Multi-Armed Bandit problem constitutes an archetypal setting for sequential decision-making, permeating multiple domains including engineering, business, and medicine.

Decision Making

Incorporating Knowledge into Structural Equation Models using Auxiliary Variables

no code implementations10 Nov 2015 Bryant Chen, Judea Pearl, Elias Bareinboim

This cancellation allows the auxiliary variables to help conventional methods of identification (e. g., single-door criterion, instrumental variables, half-trek criterion), as well as model testing (e. g., d-separation, over-identification).

External Validity: From Do-Calculus to Transportability Across Populations

no code implementations5 Mar 2015 Judea Pearl, Elias Bareinboim

The generalizability of empirical findings to new environments, settings or populations, often called "external validity," is essential in most scientific explorations.

Transportability from Multiple Environments with Limited Experiments: Completeness Results

no code implementations NeurIPS 2014 Elias Bareinboim, Judea Pearl

This paper addresses the problem of $mz$-transportability, that is, transferring causal knowledge collected in several heterogeneous domains to a target domain in which only passive observations and limited experimental data can be collected.

A General Algorithm for Deciding Transportability of Experimental Results

no code implementations29 Dec 2013 Elias Bareinboim, Judea Pearl

Generalizing empirical findings to new environments, settings, or populations is essential in most scientific explorations.

Transportability from Multiple Environments with Limited Experiments

no code implementations NeurIPS 2013 Elias Bareinboim, Sanghack Lee, Vasant Honavar, Judea Pearl

This paper considers the problem of transferring experimental findings learned from multiple heterogeneous domains to a target environment, in which only limited experiments can be performed.

Cannot find the paper you are looking for? You can Submit a new open access paper.