Theoretically Accurate Regularization Technique for Matrix Factorization based Recommender Systems

by   Hao Wang, et al.

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.


MatMat: Matrix Factorization by Matrix Fitting

Matrix factorization is a widely adopted recommender system technique th...

KL-Mat : Fair Recommender System via Information Geometry

Recommender system has intrinsic problems such as sparsity and fairness....

Optimal hybrid parameter selection for stable sequential solution of inverse heat conduction problem

To deal with the ill-posed nature of the inverse heat conduction problem...

LambdaOpt: Learn to Regularize Recommender Models in Finer Levels

Recommendation models mainly deal with categorical variables, such as us...

Towards a Better Understanding of Linear Models for Recommendation

Recently, linear regression models, such as EASE and SLIM, have shown to...

Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables

Sparse regularization such as ℓ_1 regularization is a quite powerful and...

No Cross-Validation Required: An Analytical Framework for Regularized Mixed-Integer Problems (Extended Version)

This paper develops a method to obtain the optimal value for the regular...