# Efficient sparse probability measures recovery via Bregman gradient

arXiv: https://arxiv.org/abs/2403.02861 · HTML: https://mlsanity.com/paper/2403.02861/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2024.

## Built on by (most cited first, 1 of 1)

- [Foundations of Top-k Decoding For Language Models](https://mlsanity.com/paper/2505.19371/) (2025)

## Abstract (arXiv)

This paper presents an algorithm tailored for the efficient recovery of sparse probability measures incorporating ℓ0-sparse regularization within the probability simplex constraint. Employing the Bregman proximal gradient method, our algorithm achieves sparsity by explicitly solving underlying subproblems. We rigorously establish the convergence properties of the algorithm, showcasing its capacity to converge to a local minimum with a convergence rate of O(1/k) under mild assumptions. To substantiate the efficacy of our algorithm, we conduct numerical experiments, offering a compelling demonstration of its efficiency in recovering sparse probability measures.