Keywords: Pipeline optimization, meta-learning, bayesian optimization, representation learning
TL;DR: How to learn Machine Learning pipelines representations to improve their optimization
Abstract: Finding accurate Machine Learning pipelines is essential in achieving state-of-the-art AI predictive performance. Unfortunately, most existing Pipeline Optimization techniques rely on flavors of Bayesian Optimization that do not explore the deep interaction between pipeline stages/components (e.g. between hyperparameters of the deployed preprocessing algorithm and the hyperparameters of a classifier). In this paper, we are the first to capture the deep interaction between components of a Machine Learning pipeline. We propose embedding pipelines in a deep latent representation through a novel per-component encoder mechanism. Such pipeline embeddings are used with deep kernel Gaussian Process surrogates inside a Bayesian Optimization setup. Through extensive experiments on large-scale meta-datasets, we demonstrate that learning pipeline embeddings with Deep Neural Networks significantly advances the state-of-the-art in Pipeline Optimization.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning