Deep Generative Modeling with Backward Stochastic Differential Equations

Xingcheng Xu
4/8/2023
cs.LGmath.PRstat.ML

No official code found. Best implementation: xingchengxu/BSDE-Gen (7 stars, last commit 2023-04-11).

Abstract

This paper proposes a novel deep generative model, called BSDE-Gen, which combines the flexibility of backward stochastic differential equations (BSDEs) with the power of deep neural networks for generating high-dimensional complex target data, particularly in the field of image generation. The incorporation of stochasticity and uncertainty in the generative modeling process makes BSDE-Gen an effective and natural approach for generating high-dimensional data. The paper provides a theoretical framework for BSDE-Gen, describes its model architecture, presents the maximum mean discrepancy (MMD) loss function used for training, and reports experimental results.

View on arXivView PDF

Code Implementations(1)

xingchengxu/BSDE-GenCommunity100%

BSDE-Gen, a novel deep generative model based on BSDEs (backward stochastic differential equations).

71PythonMar 31, 20233 years ago

Similar Papers

Reverse-BSDE Monte Carlo

87% match2025

Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation

85% match2023

A backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations

84% match2024

Deep Operator BSDE: a Numerical Scheme to Approximate Solution Operators

82% match1 repo2024

Neural Expectation Operators

80% match2025

A Deep Learning-Based Method for Fully Coupled Non-Markovian FBSDEs with Applications

80% match2025

Cite this paper

@article{xu2023deep,
  title  = {Deep Generative Modeling with Backward Stochastic Differential Equations},
  author = {Xingcheng Xu},
  year   = {2023},
  eprint = {2304.04049},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.04049v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.04049.svg)](https://codeofpaper.com/paper/2304.04049)

Discussion