Benamou--Brenier
PulseAugur coverage of Benamou--Brenier — every cluster mentioning Benamou--Brenier across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New algorithm learns branched generative flows for high-dimensional data
Researchers have developed a novel, scalable algorithm for branched flow matching, adapting the Benamou-Brenier optimal transport formulation to learn generative flows that mimic natural branching structures. This metho…
-
New Advective Fisher-Rao Metric Enhances Probability Measure Optimization
Researchers have introduced a new advective Fisher-Rao metric designed for optimization tasks involving probability measures governed by the continuity equation. This metric has been demonstrated to provide optimal desc…
-
New PMOT Framework Uses Continuous Normalizing Flows for Optimal Transport
Researchers have introduced Potential Matching Optimal Transport (PMOT), a novel framework utilizing continuous normalizing flows to address general $p$-cost optimal transport problems. PMOT parameterizes the flow's vel…
-
New paper details structured approximations for probability measures in Wasserstein-p distance
This paper explores how to approximate probability measures using structured methods, particularly within the Wasserstein-p distance. The research focuses on applications in machine learning, imaging, and sensor-constra…
-
New Sliced Wasserstein Steering method tackles high-dimensional probability law control
Researchers have developed a new method for steering probability distributions in high-dimensional spaces, addressing the challenges posed by ambient-space formulations. This sliced feedback controller projects evolving…