most citedDST: Data Selection and joint Training for Learning with Noisy Labels

1 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

math.OC20211 cited

NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning

Minghan Yang, Dong Xu, Qiwen Cui +2

In this paper, a novel second-order method called NG+ is proposed. By following the rule ``the shape of the gradient equals the shape of the parameter", we define a generalized fis…

cs.CV20211 cited

DST: Data Selection and joint Training for Learning with Noisy Labels

Yi Wei, Xue Mei, Xin Liu +1

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotat…

quant-ph2020

Simulating noisy variational quantum eigensolver with local noise models

Jinfeng Zeng, Zipeng Wu, Chenfeng Cao +4

Variational quantum eigensolver (VQE) is promising to show quantum advantage on near-term noisy-intermediate-scale quantum (NISQ) computers. One central problem of VQE is the effec…

physics.chem-ph2020

The impacts of optimization algorithm and basis size on the accuracy and efficiency of variational quantum eigensolver

Xian-Hu Zha, Chao Zhang, Dengdong Fan +4

Variational quantum eigensolver (VQE) is demonstrated to be the promising methodology for quantum chemistry based on near-term quantum devices. However, many problems are yet to be…

math.OC2020

Sketchy Empirical Natural Gradient Methods for Deep Learning

Minghan Yang, Dong Xu, Zaiwen Wen +2

In this paper, we develop an efficient sketchy empirical natural gradient method (SENG) for large-scale deep learning problems. The empirical Fisher information matrix is usually l…

quant-ph2020

Simulating Noisy Quantum Circuits with Matrix Product Density Operators

Song Cheng, Chenfeng Cao, Chao Zhang +4

Simulating quantum circuits with classical computers requires resources growing exponentially in terms of system size. Real quantum computer with noise, however, may be simulated p…