iALS++: Speeding up Matrix Factorization with Subspace Optimization

1 code implementation • 26 Oct 2021 • Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

However, iALS does not scale well with large embedding dimensions, d, due to its cubic runtime dependency on d. Coordinate descent variations, iCD, have been proposed to lower the complexity to quadratic in d. In this work, we show that iCD approaches are not well suited for modern processors and can be an order of magnitude slower than a careful iALS implementation for small to mid scale embedding sizes (d ~ 100) and only perform better than iALS on large embeddings d ~ 1000.

Revisiting the Performance of iALS on Item Recommendation Benchmarks

2 code implementations • 26 Oct 2021 • Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications.

Collaborative Filtering Recommendation Systems

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems

2 code implementations • 4 May 2019 • Steffen Rendle, Li Zhang, Yehuda Koren

Numerical evaluations with comparisons to baselines play a central role when judging research in recommender systems.

Collaborative Filtering Recommendation Systems