Optimal transport for machine learning: theory and applications

dc.contributor.advisorMendes, Eduardo Fonseca
dc.contributor.authorBarreira, Davi Sales
dc.contributor.memberOliveira, Roberto Imbuzeiro
dc.contributor.memberPaccanaro, Alberto
dc.contributor.unidadefgvEscolas::EMAppor
dc.date.accessioned2021-04-26T13:39:07Z
dc.date.available2021-04-26T13:39:07Z
dc.date.issued2021-03-25
dc.degree.date2021-03-25
dc.description.abstractO que os operadores de produção de petróleo valorizam ao comprar produtos químicos?: uma análise sobre a percepção de valor na decisão de compra ou contratação de um provedor de especialidades químicas no mercado de óleo e gásIn recent years, advances in Optimal Transport have led to a surge of applications in fields such as Economics, Quantitative Finance and Signal Processing, among others. One area in which it has been found particularly successful is Machine Learning. The development of computationally efficient methods for solving Optimal Transport problems opened doors for creating Machine Learning algorithms using concepts from Optimal Transport. These new algorithms encompass many different sub-areas such as Transfer Learning, Clustering, Dimensionality Reduction, Generative Models, just to name some. This work provides an overview of the different ways in which Optimal Transport has been used in Machine Learning, thus helping Machine Learning researchers to better understand its impact in the field and how to use it. This thesis first introduces the main theoretical and computational aspects of Optimal Transport theory in an accessible way to Machine Learning researchers, followed by a semi-systematic literature review focusing on the main uses of Optimal Transport in Machine Learning.eng
dc.identifier.urihttps://hdl.handle.net/10438/30407
dc.language.isoeng
dc.subjectOptimal transporteng
dc.subjectWasserstein distanceeng
dc.subjectMachine learningeng
dc.subjectLiterature revieweng
dc.subjectDistância de Wassersteinpor
dc.subject.areaMatemáticapor
dc.subject.bibliodataProblemas de transporte (Programação)por
dc.subject.bibliodataAprendizado do computadorpor
dc.subject.bibliodataOtimização matemáticapor
dc.subject.bibliodataAnálise combinatóriapor
dc.titleOptimal transport for machine learning: theory and applicationseng
dc.typeDissertationeng
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Carregando...
Imagem de Miniatura
Nome:
MasterDissertation-DaviSalesBarreira.pdf
Tamanho:
4.29 MB
Formato:
Adobe Portable Document Format
Descrição:
Dissertação
Licença do Pacote
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
license.txt
Tamanho:
4.6 KB
Formato:
Item-specific license agreed upon to submission
Descrição: