# Determinantal Point Processes for Mini-Batch Diversification

arXiv: https://arxiv.org/abs/1705.00607 · HTML: https://mlsanity.com/paper/1705.00607/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 8 of 8)

- [Variance Reduced Training with Stratified Sampling for Forecasting Models](https://mlsanity.com/paper/2103.02062/) (2021)
- [Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD](https://mlsanity.com/paper/2112.06007/) (2021)
- [Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes](https://mlsanity.com/paper/2107.01622/) (2021)
- [Data-Aware Device Scheduling for Federated Edge Learning](https://mlsanity.com/paper/2102.09491/) (2021)
- [Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes](https://mlsanity.com/paper/2207.00486/) (2022)
- [Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks](https://mlsanity.com/paper/2104.02373/) (2021)
- [Preferential Subsampling for Stochastic Gradient Langevin Dynamics](https://mlsanity.com/paper/2210.16189/) (2022)
- [MASCOT: Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval](https://mlsanity.com/paper/2608.12532/) (2026)

## Abstract (arXiv)

We study a mini-batch diversification scheme for stochastic gradient descent (SGD). While classical SGD relies on uniformly sampling data points to form a mini-batch, we propose a non-uniform sampling scheme based on the Determinantal Point Process (DPP). The DPP relies on a similarity measure between data points and gives low probabilities to mini-batches which contain redundant data, and higher probabilities to mini-batches with more diverse data. This simultaneously balances the data and leads to stochastic gradients with lower variance. We term this approach Diversified Mini-Batch SGD (DM-SGD). We show that regular SGD and a biased version of stratified sampling emerge as special cases. Furthermore, DM-SGD generalizes stratified sampling to cases where no discrete features exist to bin the data into groups. We show experimentally that our method results more interpretable and diverse features in unsupervised setups, and in better classification accuracies in supervised setups.