output
20102024
most citedRepair Locality with Multiple Erasure Tolerance

197 citations

Showing cs.LGShow all

5 papers · 1 filter

cs.LG2021★ 11 cited

Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime

Rui Zhang, Shihua Zhang

Understanding the black-box prediction for neural networks is challenging. To achieve this, early studies have designed influence function (IF) to measure the effect of removing a…

cs.LG2019★ 7 cited

Study of Constrained Network Structures for WGANs on Numeric Data Generation

Wei Wang, Chuang Wang, Tao Cui +1

Some recent studies have suggested using GANs for numeric data generation such as to generate data for completing the imbalanced numeric data. Considering the significant differenc…

cs.LG2019★ 23 cited

ChebNet: Efficient and Stable Constructions of Deep Neural Networks with Rectified Power Units via Chebyshev Approximations

Shanshan Tang, Bo Li, Haijun Yu

In a previous study [B. Li, S. Tang and H. Yu, Commun. Comput. Phy. 27(2):379-411, 2020], it is shown that deep neural networks built with rectified power units (RePU) as activatio…

cs.LG2019★ 9 cited

PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units

Bo Li, Shanshan Tang, Haijun Yu

Deep neural network with rectified linear units (ReLU) is getting more and more popular recently. However, the derivatives of the function represented by a ReLU network are not con…

cs.LG2018★ 2 cited

Application of Bounded Total Variation Denoising in Urban Traffic Analysis

Shanshan Tang, Haijun Yu

While it is believed that denoising is not always necessary in many big data applications, we show in this paper that denoising is helpful in urban traffic analysis by applying the…