Wasserstein space
PulseAugur coverage of Wasserstein space — every cluster mentioning Wasserstein space across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Wasserstein Mahalanobis distance recovers latent geometry
Researchers have introduced a new metric called the Wasserstein Mahalanobis distance, which extends the concept of Mahalanobis distance from multivariate data to probability measures. This new distance metric utilizes o…
-
New math paper details optimization on Wasserstein space
Researchers have developed new methods for optimizing functionals on Wasserstein spaces, a mathematical concept crucial for understanding probability distributions. The work establishes linear convergence for proximal d…
-
New framework for extended mean field control using reinforcement learning
Researchers have developed a novel model-free reinforcement learning framework for continuous-time extended mean field control problems. This approach utilizes deterministic feedback policies, which simplify optimizatio…
-
New Dynamic Fréchet Regression framework models evolving distributional data
Researchers have introduced Dynamic Fréchet Regression (DFR), a new statistical framework designed to model evolving distributional data over an index, such as time or depth. DFR extends Global Fréchet Regression by inc…
-
Mean-field Langevin dynamics show local exponential stability
Researchers have established the local exponential stability of the mean-field Langevin descent-ascent (MFL-DA) dynamics and its associated particle system. This work addresses a question posed by Wang and Chizat regard…
-
Deep Residual Networks Learn Geodesic Curves in Wasserstein Space
A new arXiv paper proposes that deep residual networks (ResNets) learn the geodesic curve within Wasserstein space during training. The research models ResNet forward propagation using continuity equations, suggesting t…
-
New DC programming method optimizes functionals in Wasserstein space · 2 sources tracked
Researchers have developed a new method for optimizing non-convex functionals in Wasserstein space by adapting the Difference-of-Convex (DC) programming approach. This technique, applied to functionals like Maximum Mean…
-
New Entropy-Controlled Flow Matching Method Enhances Generative Models
Researchers have introduced Entropy-Controlled Flow Matching (ECFM), a novel method for training generative models that addresses limitations in standard flow-matching objectives. ECFM enforces a global entropy-rate bud…
-
New paper models belief formation geometry under noisy observation
A new arXiv paper explores the geometric costs associated with belief formation in finite systems that operate with noisy observations. The research models the process as optimal transport in Wasserstein space, reweight…
-
Paper Unifies Diffusion Models and Flow Matching via Wasserstein Geometry
This paper explores the underlying geometry of diffusion models and flow matching, revealing that both are governed by the quadratic Wasserstein distance on the space of probability measures. The research posits that di…
-
New WT-PCA Method Analyzes Probability Measure Variations in Wasserstein Geometry
This paper introduces Wasserstein Tangential PCA (WT-PCA), a novel method for learning principal variations of probability measures within Wasserstein geometry. The approach utilizes a dynamical formulation to interpret…
-
New L2 over Wasserstein framework enhances optimal transport for random measures
Researchers have introduced a new framework called $L^2$ over Wasserstein space to address statistical uncertainty in optimal transport. This framework extends the classical theory to random probability measures, preser…
-
New MMFLD method optimizes probability measures on constrained domains
Researchers have introduced Mirror Mean-Field Langevin Dynamics (MMFLD) to address optimization problems with constrained domains in probability measures. This new method extends existing mean-field algorithms, which ar…
-
New Newton-Type Method Accelerates Optimization on Wasserstein Space
Researchers have developed a new second-order optimization method called Wasserstein Saddle-Free Newton (WSFN) to address challenges in minimizing non-convex functionals over Wasserstein space. This method aims to overc…
-
New OptMuon method enhances stochastic optimization with adaptive momentum
Researchers have introduced OptMuon, a novel adaptive momentum orthogonalization method for stochastic nonconvex optimization that calibrates update magnitudes from observed trajectories. This approach combines Muon-sty…