Research map / Optimization / Optimizers
Variational Wasserstein gradient flow
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use variational JKO-Flow instead of VGrow | CIFAR10 image generation · CIFAR10 unconditional | FID: 28.8 -> 23.1 | Helped |
| Use variational JKO-Flow instead of GLOW | CIFAR10 image generation · CIFAR10 unconditional | FID: 45.99 -> 23.1 | Helped |
| Use variational JKO-Flow instead of WGAN-GP | CIFAR10 image generation · CIFAR10 unconditional | FID: 31.1 -> 23.1 | Helped |
| Use variational JKO-Flow instead of SN-GAN | CIFAR10 image generation · CIFAR10 unconditional | FID: 21.7 -> 23.1 | Hurt |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · covtype | accuracy: 0.75 -> 0.753 | Helped |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · covtype | log-likelihood: -0.515 -> -0.528 | Hurt |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · splice | accuracy: 0.845 -> 0.84 | Hurt |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · splice | log-likelihood: -0.36 -> -0.38 | Hurt |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · waveform | accuracy: 0.78 -> 0.785 | Helped |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · waveform | log-likelihood: -0.485 -> -0.455 | Helped |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · image | accuracy: 0.82 -> 0.866 | Helped |
| Use the proposed sampler instead of JKO-ICNN | Bayesian logistic regression · image | log-likelihood: -0.43 -> -0.394 | Helped |
Closest papers by meaning
- Flowing Datasets with Wasserstein over Wasserstein Gradient Flows (ICML 2025 · similarity 0.88)
- Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points (NeurIPS 2025 · similarity 0.88)
- Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport (ICML 2024 · similarity 0.87)
- Minimizing $f$-Divergences by Interpolating Velocity Fields (ICML 2024 · similarity 0.87)
- Mirror and Preconditioned Gradient Descent in Wasserstein Space (NeurIPS 2024 · similarity 0.87)
- Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.