Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that each fraction of an epoch comprises an independent random sample of the training data that may not preserve informative structure present in the full data. We hypothesize that the training can be more effective with self-similar arrangements that potentially allow each epoch to provide benefits of multiple ones. We study this for "matrix factorization" - the common task of learning metric embeddings of entities such as queries, videos, or words from example pairwise associations. We construct arrangements that preserve the weighted Jaccard similarities of rows and columns and experimentally observe training acceleration of 3%-37% on synthetic and recommendation datasets. Principled arrangements of training examples emerge as a novel and potentially powerful enhancement to SGD that merits further exploration.
|Title of host publication||36th International Conference on Machine Learning, ICML 2019|
|Publisher||International Machine Learning Society (IMLS)|
|Number of pages||13|
|State||Published - 2019|
|Event||36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States|
Duration: 9 Jun 2019 → 15 Jun 2019
|Name||36th International Conference on Machine Learning, ICML 2019|
|Conference||36th International Conference on Machine Learning, ICML 2019|
|Period||9/06/19 → 15/06/19|
Bibliographical noteFunding Information:
We are grateful to the anonymous ICML 2019 reviewers for many helpful comments that allowed us to improve the presentation. This research is partially supported by the Israel Science Foundation (Grant No. 1841/14).
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved.