Loading Now

Summary of Decor: Deconfounding Time Series with Robust Regression, by Felix Schur et al.


DecoR: Deconfounding Time Series with Robust Regression

by Felix Schur, Jonas Peters

First submitted to arxiv on: 11 Jun 2024

Categories

  • Main: Machine Learning (stat.ML)
  • Secondary: Machine Learning (cs.LG)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
The proposed paper addresses a challenging problem in causal inference on time series data, specifically when there are unobserved confounders present. The authors introduce Deconfounding by Robust regression (DecoR), a novel approach that leverages robust linear regression in the frequency domain to estimate the causal effect between two time series. DecoR builds upon two different robust regression techniques and improves existing bounds on estimation error without requiring distributional assumptions on the covariates. The authors demonstrate DecoR’s effectiveness through experiments on both synthetic and real-world data from Earth system science, including simulations that suggest its robustness to model misspecification.
Low GrooveSquid.com (original content) Low Difficulty Summary
This research paper is about using math and statistics to understand how things change over time. It’s trying to figure out what causes something to happen when we can’t see all the factors at play. The scientists developed a new method called DecoR, which helps us get more accurate answers by looking at the data in a special way. They tested it on some real-world data and showed that it works well, even if our initial assumptions aren’t exactly right.

Keywords

» Artificial intelligence  » Inference  » Linear regression  » Regression  » Time series