Simple and Near-Optimal MAP Inference for Nonsymmetric DPPs

02/10/2021
by   Nima Anari, et al.
0

Determinantal point processes (DPPs) are widely popular probabilistic models used in machine learning to capture diversity in random subsets of items. While traditional DPPs are defined by a symmetric kernel matrix, recent work has shown a significant increase in the modeling power and applicability of models defined by nonsymmetric kernels, where the model can capture interactions that go beyond diversity. We study the problem of maximum a posteriori (MAP) inference for determinantal point processes defined by a nonsymmetric positive semidefinite matrix (NDPPs), where the goal is to find the maximum k× k principal minor of the kernel matrix L. We obtain the first multiplicative approximation guarantee for this problem using local search, a method that has been previously applied to symmetric DPPs. Our approximation factor of k^O(k) is nearly tight, and we show theoretically and experimentally that it compares favorably to the state-of-the-art methods for this problem that are based on greedy maximization. The main new insight enabling our improved approximation factor is that we allow local search to update up to two elements of the solution in each iteration, and we show this is necessary to have any multiplicative approximation guarantee.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

07/06/2019

Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm

"Composable core-sets" are an efficient framework for solving optimizati...
05/30/2019

Learning Nonsymmetric Determinantal Point Processes

Determinantal point processes (DPPs) have attracted substantial attentio...
06/17/2020

Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes

Determinantal point processes (DPPs) have attracted significant attentio...
11/01/2018

Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem

Symmetric determinantal point processes (DPP's) are a class of probabili...
07/09/2020

Some algorithms for maximum volume and cross approximation of symmetric semidefinite matrices

Finding the r× r submatrix of maximum volume of a matrix A∈ℝ^n× n is an ...
11/17/2018

Deep Determinantal Point Processes

Determinantal point processes (DPPs) have attracted significant attentio...
01/23/2020

Best Principal Submatrix Selection for the Maximum Entropy Sampling Problem: Scalable Algorithms and Performance Guarantees

This paper studies a classic maximum entropy sampling problem (MESP), wh...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.