DOCPRO: A Framework for Building Document Processing Systems

Huang, Ming-Jen; Huang, Chiung-Shing; Wei, Chiching

doi:10.5121/csit.2020.100917

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this subsection, we provide the convergence properties of our AdaMSGDA algorithm under the above Assumptions 1-5. We first give a mild assumption 5, which is commonly used in adaptive algorithms [Huang et al, 2021a].…”

Section: Convergence Analysis Of Adamsgda Algorithmmentioning

confidence: 99%

“…Assumption 5 ensures that the adaptive matrices A t and B t for all t ≥ 1 are positive definite as in [Huang et al, 2021a[Huang et al, , 2023. Note that Huang et al [2023] only provided the convergence properties of both the AdaGDA and VR-AdaGDA when they use the global adaptive learning rates (i.e., B t = b t I p (b t > 0)) to update the dual variable y.…”

Section: Convergence Analysis Of Adamsgda Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Smellscapes of Nanjing Road

Huang¹

2022

Sensing China

View full text Add to dashboard Cite

Bilevel optimization is a popular two-level hierarchical optimization, which has been widely applied to many machine learning tasks such as hyperparameter learning, meta learning and continual learning. Although many bilevel optimization methods recently have been developed, the bilevel methods are not well studied when the lower-level problem is nonconvex. To fill this gap, in the paper, we study a class of nonconvex bilevel optimization problems, which both upper-level and lower-level problems are nonconvex, and the lower-level problem satisfies Polyak-Lojasiewicz (PL) condition. We propose an efficient momentum-based gradient bilevel method (MGBiO) to solve these deterministic problems. Meanwhile, we propose a class of efficient momentum-based stochastic gradient bilevel methods (MSGBiO and VR-MSGBiO) to solve these stochastic problems. Moreover, we provide a useful convergence analysis framework for our methods. Specifically, under some mild conditions, we prove that our MGBiO method has a sample (or gradient) complexity of O(ǫ −2 ) for finding an ǫ-stationary solution of the deterministic bilevel problems (i.e., ∇F (x) ≤ ǫ), which improves the existing best results by a factor of O(ǫ −1 ). Meanwhile, we prove that our MSGBiO and VR-MSGBiO methods have sample complexities of Õ(ǫ −4 ) and Õ(ǫ −3 ), respectively, in finding an ǫ-stationary solution of the stochastic bilevel problems (i.e., E ∇F (x) ≤ ǫ), which improves the existing best results by a factor of O(ǫ −3 ). This manuscript commemorates the mathematician Boris Polyak (1935 -2023).

show abstract

Section: Convergence Analysis Of Adamsgda Algorithmmentioning

confidence: 99%

Section: Convergence Analysis Of Adamsgda Algorithmmentioning

confidence: 99%

Smellscapes of Nanjing Road

Huang¹

2022

Sensing China

View full text Add to dashboard Cite

show abstract

Taxonomia de coisas para o dataismo

Schiel

2022

logeion

View full text Add to dashboard Cite

Existe uma tendência evidente de computadorizar cada vez mais atividades do dia-a-dia. Ferramentas de IA, de tomada de decisão e aprendizado de máquina são algumas destas tecnologias. Neste artigo analisamos como a modelagem de aplicações de bancos de dados deve evoluir para atender a estes requisitos. Coisas estruturais e ocorrêncais adequadas são consideradas e, para cada conceito, têm que ser definidas regras que garantem a integridade do sistema como um todo. Caracteristicas específicas de sistemas complexos ativos e/ou reativos, questões de autonomia, aspectos espaciais e temporais, assim como informações imprecisas, devem ser levados em consideração.

show abstract

DOCPRO: A Framework for Building Document Processing Systems

Cited by 2 publications

References 9 publications

Smellscapes of Nanjing Road

Smellscapes of Nanjing Road

Taxonomia de coisas para o dataismo

Contact Info

Product

Resources

About