# Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems

arXiv: https://arxiv.org/abs/2205.10492 · HTML: https://mlsanity.com/paper/2205.10492/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 9 references that are in the map.
- First posted on arXiv 21 May 2022.

## Builds on (most cited first, 4 of 4)

- [MatRec: Matrix Factorization for Highly Skewed Dataset](https://mlsanity.com/paper/2011.04395/) (2020)
- [Zipf Matrix Factorization : Matrix Factorization with Matthew Effect Reduction](https://mlsanity.com/paper/2106.07347/) (2021)
- [ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data](https://mlsanity.com/paper/2112.03084/) (2021)
- [MatMat: Matrix Factorization by Matrix Fitting](https://mlsanity.com/paper/2112.03089/) (2021)

## Built on by (most cited first, 1 of 1)

- [Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation](https://mlsanity.com/paper/2506.10658/) (2025)

## Abstract (arXiv)

Regularization is a popular technique to solve the overfitting problem of machine learning algorithms. Most regularization technique relies on parameter selection of the regularization coefficient. Plug-in method and cross-validation approach are two most common parameter selection approaches for regression methods such as Ridge Regression, Lasso Regression and Kernel Regression. Matrix factorization based recommendation system also has heavy reliance on the regularization technique. Most people select a single scalar value to regularize the user feature vector and item feature vector independently or collectively. In this paper, we prove that such approach of selecting regularization coefficient is invalid, and we provide a theoretically accurate method that outperforms the most widely used approach in both accuracy and fairness metrics.