How to "DODGE" Complex Software Analytics?

Amritanshu Agrawal, Wei Fu, Di Chen, Xipeng Shen, Tim Menzies

Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i.e., automatic tools that find good settings for a learner's control parameters. We show that such hyperparameter optimization can be unnecessarily slow, particularly when the optimizers waste time exploring "redundant tunings"', i.e., pairs of tunings which lead to indistinguishable results. By ignoring redundant tunings, DODGE, a tuning tool, runs orders of magnitude faster, while also generating learners with more accurate predictions than seen in prior state-of-the-art approaches.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment