Low-Rank Factorization of Determinantal Point Processes (2016-02-17T00:00:00.000000Z)

TL;DR

This work presents a new method for learning the DPP kernel from observed data using a low-rank factorization of this kernel, enabling a learning algorithm that is nearly an order of magnitude faster than previous approaches, while also providing for a method for computing product recommendation predictions that is far faster than previously techniques that involve a full-rank DPP Kernel.

Abstract

Determinantal point processes (DPPs) have garnered attention as an elegant probabilistic model of set diversity. They are useful for a number of subset selection tasks, including product recommendation. DPPs are parametrized by a positive semi-definite kernel matrix. In this work we present a new method for learning the DPP kernel from observed data using a low-rank factorization of this kernel. We show that this low-rank factorization enables a learning algorithm that is nearly an order of magnitude faster than previous approaches, while also providing for a method for computing product recommendation predictions that is far faster (up to 20x faster or more for large item catalogs) than previous techniques that involve a full-rank DPP kernel. Furthermore, we show that our method provides equivalent or sometimes better test log-likelihood than prior full-rank DPP approaches.

Authors

U. Paquet

2 papers

Noam Koenigstein

3 papers

Mike Gartrell

1 papers

TL;DR

Abstract

Authors

References38 items

Kronecker Determinantal Point Processes

Learning Probabilistic Submodular Diversity Models Via Noise Contrastive Estimation

Fast DPP Sampling for Nystrom with Application to Kernel Methods

Monte Carlo Markov Chain Algorithms for Sampling Strongly Rayleigh Distributions and Determinantal Point Processes

Diversity Networks

A Probabilistic Model for Using Social Networks in Personalized Item Recommendation

Efficient Sampling for k-Determinantal Point Processes

Scalable Recommendation with Hierarchical Poisson Factorization

Fixed-point algorithms for learning determinantal point processes

Large-Margin Determinantal Point Processes

Expectation-Maximization for Learning Determinantal Point Processes

Learning the Parameters of Determinantal Point Process Kernels

A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data

Fast Determinantal Point Process Sampling with Application to Clustering

Approximate Inference in Continuous Determinantal Processes

One-class collaborative filtering with random graphs

Nystrom Approximation for Large-Scale Determinantal Processes

Priors for Diversity in Generative Latent Variable Models

Determinantal Point Processes for Machine Learning

Item popularity and recommendation accuracy

Learning Determinantal Point Processes

k-DPPs: Fixed-Size Determinantal Point Processes

Structured Determinantal Point Processes

Improving one-class collaborative filtering by incorporating rich user information

Collaborative Filtering for Implicit Feedback Datasets

Classification-based collaborative filtering using market basket data

An improved collaborative filtering approach for predicting cross-category purchases based on binary market basket data

Using association rules for product assortment decisions: a case study

Integrating Classification and Association Rule Mining

Mining association rules between sets of items in large databases

The coincidence approach to stochastic point processes

A Stochastic Approximation Method

Approximate inference for determinantal point processes

Association Rules Mining: A Recent Overview

Retail market basket data set

A method of solving a convex programming problem with convergence rate O(1/sqr(k))

TLUCS KDD implementation of CBA (classiﬁcation based on associations)

Poisson Factorization (PF)

Field of Study

Venue Information

Name

Type

URL

Alternate Names