A unifying causal framework for analyzing dataset shift-stable learning algorithms

Journal of Causal Inference 10 (1):64-89 (2022)
  Copy   BIBTEX

Abstract

Recent interest in the external validity of prediction models has produced many methods for finding predictive distributions that are invariant to dataset shifts and can be used for prediction in new, unseen environments. However, these methods consider different types of shifts and have been developed under disparate frameworks, making it difficult to theoretically analyze how solutions differ with respect to stability and accuracy. Taking a causal graphical view, we use a flexible graphical representation to express various types of dataset shifts. Given a known graph of the data generating process, we show that all invariant distributions correspond to a causal hierarchy of graphical operators, which disable the edges in the graph that are responsible for the shifts. The hierarchy provides a common theoretical underpinning for understanding when and how stability to shifts can be achieved, and in what ways stable distributions can differ. We use it to establish conditions for minimax optimal performance across environments, and derive new algorithms that find optimal stable distributions. By using this new perspective, we empirically demonstrate that that there is a tradeoff between minimax and average performance.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 90,616

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Fraudulent Financial Transactions Detection Using Machine Learning.Mosa M. M. Megdad, Samy S. Abu-Naser & Bassem S. Abu-Nasser - 2022 - International Journal of Academic Information Systems Research (IJAISR) 6 (3):30-39.
The three faces of faithfulness.Jiji Zhang & Peter Spirtes - 2016 - Synthese 193 (4):1011-1027.
A causal framework for integrating learning and reasoning.David A. Lagnado - 2009 - Behavioral and Brain Sciences 32 (2):211-212.
Projecting sequential algorithms on strongly stable functions.Thomas Ehrhard - 1996 - Annals of Pure and Applied Logic 77 (3):201-244.

Analytics

Added to PP
2022-05-20

Downloads
16 (#774,541)

6 months
6 (#202,901)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Citations of this work

No citations found.

Add more citations