Summary of Deep Mmd Gradient Flow Without Adversarial Training, by Alexandre Galashov et al.
Deep MMD Gradient Flow without adversarial training
by Alexandre Galashov, Valentin de Bortoli, Arthur Gretton
First submitted to arxiv on: 10 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed gradient flow procedure for generative modeling uses a noise-adaptive Wasserstein Gradient of the Maximum Mean Discrepancy (MMD) to transport particles from an initial source distribution to a target distribution. The approach, called Diffusion-MMD-Gradient Flow or DMMD, is trained on data distributions corrupted by increasing levels of noise obtained via forward diffusion processes. This generalizes MMD Gradient Flow and achieves competitive performance in unconditional image generation tasks like CIFAR10, MNIST, CELEB-A (64 x 64), and LSUN Church (64 x 64). Additionally, the approach can be applied with a lower bound on the KL divergence instead of MMD. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to create images that are similar to real ones is proposed. It’s like a step-by-step process where particles move from one place to another based on how different they are. This helps train a model that can generate good-looking pictures. The method was tested and worked well for things like faces, houses, and other common objects. |
Keywords
» Artificial intelligence » Diffusion » Image generation
