Learning and Sampling of Atomic Interventions from Observations

Authors: Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, Ashwin Maran, Vinodchandran N. Variyam

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the problem of efficiently estimating the effect of an intervention on a single variable (atomic interventions) using observational samples in a causal Bayesian network. Our goal is to give algorithms that are efficient in both time and sample complexity in a non-parametric setting. We design sample and time efficient algorithms for the above-mentioned estimation problems. We present an efficient algorithm for the evaluation and generation problems. Finally we establish a lower bound for the sample complexity showing that our sample complexity has optimal dependence on the parameters n and ε, as well as if k = 1 on the strong positivity parameter.
Researcher Affiliation Academia 1National University of Singapore 2Cornell University 3University of Wisconsin-Madison 4University of Nebraska-Lincoln.
Pseudocode Yes Algorithm 1 Learning Dx
Open Source Code No No explicit statement about providing open-source code for the methodology described in this paper was found. The paper mentions other open-source tools like 'causality', 'Do Why', and 'CIBN' in the related work section, but not for their own work.
Open Datasets No No specific publicly available dataset is mentioned or linked. The paper refers to 'samples from the observational distribution P' in a theoretical context.
Dataset Splits No No specific dataset split information (training, validation, or testing) is provided, as the paper presents theoretical algorithms and analyses rather than empirical evaluations.
Hardware Specification No No specific hardware details (like CPU/GPU models, memory) used for running experiments were found. The paper focuses on theoretical algorithm design and analysis.
Software Dependencies No No specific ancillary software details with version numbers (e.g., library or solver names) are provided for the algorithms developed in this paper.
Experiment Setup No No specific experimental setup details, such as hyperparameter values, training configurations, or system-level settings, are provided. The paper is theoretical and focuses on algorithm design and analysis.