Large-Margin Matrix Factorization
نویسندگان
چکیده
We present a novel approach to collaborative prediction, using low-norm instead of low-rank factorizations. The approach is inspired by, and has strong connections to, large-margin linear discrimination. We show how to learn low-norm factorizations by solving a semi-definite program, and present generalization error bounds based on analyzing the Rademacher complexity of low-norm factorizations.
منابع مشابه
Nonparametric Max-Margin Matrix Factorization for Collaborative Prediction
We present a probabilistic formulation of max-margin matrix factorization and build accordingly a nonparametric Bayesian model which automatically resolves the unknown number of latent factors. Our work demonstrates a successful example that integrates Bayesian nonparametrics and max-margin learning, which are conventionally two separate paradigms and enjoy complementary advantages. We develop ...
متن کاملA social recommender system based on matrix factorization considering dynamics of user preferences
With the expansion of social networks, the use of recommender systems in these networks has attracted considerable attention. Recommender systems have become an important tool for alleviating the information that overload problem of users by providing personalized recommendations to a user who might like based on past preferences or observed behavior about one or various items. In these systems...
متن کاملA Modified Digital Image Watermarking Scheme Based on Nonnegative Matrix Factorization
This paper presents a modified digital image watermarking method based on nonnegative matrix factorization. Firstly, host image is factorized to the product of three nonnegative matrices. Then, the centric matrix is transferred to discrete cosine transform domain. Watermark is embedded in low frequency band of this matrix and next, the reverse of the transform is computed. Finally, watermarked ...
متن کاملSparse Learning via Maximum Margin Matrix Factorization
In this paper, an algorithm for sparse learning via Maximum Margin Matrix Factorization(MMMF) is proposed. The algorithm is based on L1 penality and Alternating Direction Method of Multipliers. It shows that with sparse factors, sparse factors method can obtain result as good as dense factors.
متن کاملMaximum-Margin Matrix Factorization
We present a novel approach to collaborative prediction, using low-norm instead of low-rank factorizations. The approach is inspired by, and has strong connections to, large-margin linear discrimination. We show how to learn low-norm factorizations by solving a semi-definite program, and discuss generalization error bounds for them.
متن کاملMatrix completion and low-rank SVD via fast alternating least squares
The matrix-completion problem has attracted a lot of attention, largely as a result of the celebrated Netflix competition. Two popular approaches for solving the problem are nuclear-norm-regularized matrix approximation (Candès and Tao, 2009; Mazumder et al., 2010), and maximum-margin matrix factorization (Srebro et al., 2005). These two procedures are in some cases solving equivalent problems,...
متن کامل