A fast proximal point method for computing exact wasserstein distance

Y Xie, X Wang, R Wang, H Zha - Uncertainty in artificial …, 2020 - proceedings.mlr.press
Wasserstein distance plays increasingly important roles in machine learning, stochastic
programming and image processing. Major efforts have been under way to address its high …

Squared earth mover's distance-based loss for training deep neural networks

L Hou, CP Yu, D Samaras - arXiv preprint arXiv:1611.05916, 2016 - arxiv.org
In the context of single-label classification, despite the huge success of deep learning, the
commonly used cross-entropy loss function ignores the intricate inter-class relationships that …

AI4SeaIce: selecting loss functions for automated SAR sea ice concentration charting

A Kucik, A Stokholm - Scientific reports, 2023 - nature.com
For maritime navigation in the Arctic, sea ice charts are an essential tool, which still to this
day is drawn manually by professional ice analysts. The total Sea Ice Concentration (SIC) is …

Generative adversarial networks based on Wasserstein distance for knowledge graph embeddings

Y Dai, S Wang, X Chen, C Xu, W Guo - Knowledge-Based Systems, 2020 - Elsevier
Abstract Knowledge graph embedding aims to project entities and relations into low-
dimensional and continuous semantic feature spaces, which has captured more attention in …

Distribution-based measures of tumor heterogeneity are sensitive to mutation calling and lack strong clinical predictive power

J Noorbakhsh, H Kim, S Namburi, JH Chuang - Scientific Reports, 2018 - nature.com
Mutant allele frequency distributions in cancer samples have been used to estimate
intratumoral heterogeneity and its implications for patient survival. However, mutation calls …

[PDF][PDF] Squared earth movers distance loss for training deep neural networks on ordered-classes

L Hou, CP Yu, D Samaras - NIPS workshop, 2017 - cs.stonybrook.edu
In the context of multi-class single-label classification, the loss function of deep learning
methods compares the predicted class distribution versus the ground truth class distribution …

AI-Driven Reservoir Management: GANs and GMM for Enhanced Control

AAA Al-Fakih, A Koeshidayatullah, S Kaka - ECMOR 2024, 2024 - earthdoc.org
This research explores the novel application of ensemble generative adversarial networks
(Ensemble GANs) for modeling data distributions and detecting anomalies within well log …

[PDF][PDF] AI4SeaIce: Comparing Loss Representations for SAR Sea Ice Concentration Charting

A Kucik, A Stokholm - 2023 - researchgate.net
Sea ice charts, an important tool for navigation in the Arctic, are to this day manually drawn
by professional ice analysts. The primary descriptor of the charts–the Sea Ice Concentration …

Assessing distances between pairs of histograms based on relaxed flow constraints

K Atasu, T Mittelholzer - US Patent 11,042,604, 2021 - Google Patents
The example embodiments of the invention notably are directed to a computer-implemented
method for assessing distances between pairs of histograms. Each of the histograms is a …