Results 131 to 140 of about 4,469 (193)

Hyperbolic Wasserstein Distance for Shape Indexing. [PDF]

IEEE Trans Pattern Anal Mach Intell, 2020
Shi J, Wang Y.
europepmc   +1 more source

Wasserstein Distances, Neuronal Entanglement, and Sparsity

Disentangling polysemantic neurons is at the core of many current approaches to interpretability of large language models. Here we attempt to study how disentanglement can be used to understand performance, particularly under weight sparsity, a leading post-training optimization technique. We suggest a novel measure for estimating neuronal entanglement:
Sawmya, Shashata, Kong, Linghao, Markov, Ilia, Alistarh, Dan-Adrian, Shavit, Nir   +4 more
openaire   +4 more sources

A novel kernel Wasserstein distance on Gaussian measures: An application of identifying dental artifacts in head and neck computed tomography. [PDF]

Comput Biol Med, 2020
Oh JH, Pouryahya M, Iyer A, Apte AP, Deasy JO, Tannenbaum A.   +5 more
europepmc   +1 more source

The Observable Wasserstein Distance

We introduce the observable Wasserstein distance, a framework for deriving lower bounds on the Wasserstein distance between probability measures on Polish metric spaces, designed to bypass the computational intractability of exact optimal transport in large-scale, non-Euclidean datasets.
Santos, Edivaldo Lopes dos, Mauri, Leandro Vicente, Mio, Washington, Needham, Tom   +3 more
openaire   +2 more sources

EEG Signal Reconstruction Using a Generative Adversarial Network With Wasserstein Distance and Temporal-Spatial-Frequency Loss. [PDF]

Front Neuroinform, 2020
Luo TJ, Fan Y, Chen L, Guo G, Zhou C.
europepmc   +1 more source

Private Wasserstein Distance

Wasserstein distance is a key metric for quantifying data divergence from a distributional perspective. However, its application in privacy-sensitive environments, where direct sharing of raw data is prohibited, presents significant challenges. Existing approaches, such as Differential Privacy and Federated Optimization, have been employed to estimate ...
Li, Wenqian, Pang, Yan
openaire   +2 more sources

WNetAlign: fast and accurate spectra alignment using truncated Wasserstein distance and network simplex. [PDF]

Brief Bioinform
Król J, Bochenek M, Jopa S, Kazimierczuk K, Gambin A, Startek MP.   +5 more
europepmc   +1 more source

Detection of LUAD-Associated Genes Using Wasserstein Distance in Multiomics Feature Selection. [PDF]

Bioengineering (Basel)
Zhao S, Huang S, Yang L, Zhou W, Li K, Wang S.   +5 more
europepmc   +1 more source

Clustering Cu-S based compounds using periodic table representation and compositional Wasserstein distance. [PDF]

Sci Rep
Hao S, Xia T, Zhang R, Guo M.
europepmc   +1 more source

CONSTRUCTION OF 4D NEONATAL CORTICAL SURFACE ATLASES USING WASSERSTEIN DISTANCE. [PDF]

Proc IEEE Int Symp Biomed Imaging, 2019
Chen Z, Wu Z, Sun L, Wang F, Wang L, Lin W, Gilmore JH, Shen D, Li G.   +8 more
europepmc   +1 more source