Deep Generative Modeling with Backward Stochastic Differential Equations
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 8 Apr 2023.
Builds on
32 of 46 references.
References · 32
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2022Generative Adversarial Networkscited by 5,603
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
20 more
- 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
- 2022Diffusion Models in Vision: A Surveycited by 1,008
- 2017Solving high-dimensional partial differential equations using deep learningcited by 549
- 2017Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equationscited by 188
- 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
- 2019Neural Jump Stochastic Differential Equationscited by 147
- 2018Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equationscited by 54
- 2022Score-based Generative Modeling Secretly Minimizes the Wasserstein Distancecited by 50
- 2018Convergence of the Deep BSDE Method for Coupled FBSDEscited by 42
- 2019Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learningcited by 15
- 2019Deep Neural Network Framework Based on Backward Stochastic Differential Equations for Pricing and Hedging American Options in High Dimensionscited by 14
- 2022Learning High-Dimensional McKean-Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependencecited by 13
- 2022From Points to Functions: Infinite-dimensional Representations in Diffusion Modelscited by 11
- 2022Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problemscited by 9
- 2021Convergence of the Deep BSDE method for FBSDEs with non-Lipschitz coefficientscited by 7
- 2023Geometry of Score Based Generative Modelscited by 7
- 2023Deep learning numerical methods for high-dimensional fully nonlinear PIDEs and coupled FBSDEs with jumpscited by 6
- 2020Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equationscited by 5
- 2022Deep BSDE-ML Learning and Its Application to Model-Free Optimal Controlcited by 5
- 2022A deep learning method for solving stochastic optimal control problems driven by fully-coupled FBSDEscited by 2
Built on by
Not cited yet.