method · first seen 6 Oct 2026
JKO scheme
Also: minimizing movement scheme, Jordan-Kinderlehrer-Otto scheme
A variational time-discretisation for gradient flows in the Wasserstein space of probability measures.
Mentions per week
PapersCodeDiscussion
Earliest sources
- A Neural JKO Scheme for Hellinger-Kantorovich Gradient Flows via Monge-Growth PairsPapers · 6 Oct 2026 · Geuntaek Seo, Cheolhyeong Kim, Hwijae Son, Hyung Ju Hwang
- Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO SchemePapers · 7 Oct 2026 · Chenguang Duan, Johannes Hertrich, Gabriele Steidl
- Gradient Flows over Convex Bodies for Learning Optimal RegularizersPapers · 12 Nov 2026 · Nilava Metya, Oscar Leong, Yong Sheng Soh
Latest sources
- Gradient Flows over Convex Bodies for Learning Optimal RegularizersPapers · 12 Nov 2026 · Nilava Metya, Oscar Leong, Yong Sheng Soh
- Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO SchemePapers · 7 Oct 2026 · Chenguang Duan, Johannes Hertrich, Gabriele Steidl
- A Neural JKO Scheme for Hellinger-Kantorovich Gradient Flows via Monge-Growth PairsPapers · 6 Oct 2026 · Geuntaek Seo, Cheolhyeong Kim, Hwijae Son, Hyung Ju Hwang