activity
20192023
most citedPerformance Evaluation of Adversarial Attacks: Discrepancies and Solutions

5 citations · 13 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG20222 cited

Tucker-O-Minus Decomposition for Multi-view Tensor Subspace Clustering

Yingcong Lu, Yipeng Liu, Zhen Long +2

With powerful ability to exploit latent structure of self-representation information, different tensor decompositions have been employed into low rank multi-view clustering (LRMVC)…

cs.LG20211 cited

Semi-tensor Product-based TensorDecomposition for Neural Network Compression

Hengling Zhao, Yipeng Liu, Xiaolin Huang +1

The existing tensor networks adopt conventional matrix product for connection. The classical matrix product requires strict dimensionality consistency between factors, which can re…

cs.LG20215 cited

Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions

Jing Wu, Mingyi Zhou, Ce Zhu +3

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models. However, mainstream evaluation criteria experience limitations, eve…

cs.LG2021

Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces

Tao Li, Lei Tan, Qinghua Tao +2

Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces. In this…

cs.LG2020

A Unified Framework for Coupled Tensor Completion

Huyan Huang, Yipeng Liu, Ce Zhu

Coupled tensor decomposition reveals the joint data structure by incorporating priori knowledge that come from the latent coupled factors. The tensor ring (TR) decomposition is inv…

cs.LG2019

Robust Low-Rank Tensor Ring Completion

Huyan Huang, Yipeng Liu, Ce Zhu

Low-rank tensor completion recovers missing entries based on different tensor decompositions. Due to its outstanding performance in exploiting some higher-order data structure, low…