# DPPNet: Approximating Determinantal Point Processes with Deep Networks

arXiv: https://arxiv.org/abs/1901.02051 · HTML: https://mlsanity.com/paper/1901.02051/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2019.

## Built on by (most cited first, 5 of 5)

- [Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints](https://mlsanity.com/paper/2302.03462/) (2023)
- [Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization](https://mlsanity.com/paper/2305.18417/) (2023)
- [Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints](https://mlsanity.com/paper/2308.12680/) (2023)
- [Adaptive Quality-Diversity Trade-offs for Large-Scale Batch Recommendation](https://mlsanity.com/paper/2602.02024/) (2026)
- [MASCOT: Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval](https://mlsanity.com/paper/2608.12532/) (2026)

## Abstract (arXiv)

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(N3) preprocessing cost and an O(Nk3) 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.