DeepAI AI Chat
Log In Sign Up

DPPNet: Approximating Determinantal Point Processes with Deep Networks

by   Zelda Mariet, et al.

Determinantal Point Processes (DPPs) provide an elegant and versatile way to sample sets of items that balance the point-wise quality with the set-wise diversity of selected items. For this reason, they have gained prominence in many machine learning applications that rely on subset selection. However, sampling from a DPP over a ground set of size N is a costly operation, requiring in general an O(N^3) preprocessing cost and an O(Nk^3) sampling cost for subsets of size k. We approach this problem by introducing DPPNets: generative deep models that produce DPP-like samples for arbitrary ground sets. We develop an inhibitive attention mechanism based on transformer networks that captures a notion of dissimilarity between feature vectors. We show theoretically that such an approximation is sensible as it maintains the guarantees of inhibition or dissimilarity that makes DPPs so powerful and unique. Empirically, we demonstrate that samples from our model receive high likelihood under the more expensive DPP alternative.


page 8

page 13


Exact sampling of determinantal point processes with sublinear time preprocessing

We study the complexity of sampling from a distribution over all index s...

Kronecker Determinantal Point Processes

Determinantal Point Processes (DPPs) are probabilistic models over all s...

Differentiable Subset Sampling

Many machine learning tasks require sampling a subset of items from a co...

Optimized Algorithms to Sample Determinantal Point Processes

In this technical report, we discuss several sampling algorithms for Det...

Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem

Symmetric determinantal point processes (DPP's) are a class of probabili...

Sampling from a k-DPP without looking at all items

Determinantal point processes (DPPs) are a useful probabilistic model fo...

An Empirical Study of w-Cutset Sampling for Bayesian Networks

The paper studies empirically the time-space trade-off between sampling ...