Paper Image

Hyperparameters affect causal graph learning

Published on:

27 October 2023

Primary Category:

Machine Learning

Paper Authors:

Damian Machlanski,

Spyridon Samothrakis,

Paul Clarke

Bullets

Key Details

Hyperparameters strongly affect structure learning, incorrect values cause mistakes

Algorithms differ in performance even with optimal hyperparameters

No algorithm performs best under all conditions

Algorithms vary in robustness to misspecified hyperparameters

Fixed hyperparameters can work well, but risks remain

AI generated summary

Hyperparameters affect causal graph learning

This paper investigates how hyperparameters influence the performance of algorithms that learn causal graph structures from data. It finds hyperparameters play a key role, with incorrect values leading to mistakes in recovered graphs. The paper also shows algorithms vary in robustness to misspecified hyperparameters.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up