Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Validation Approach to Over-parameterized Matrix and Image Recovery


Sep 21, 2022
Lijun Ding, Zhen Qin, Liwei Jiang, Jinxin Zhou, Zhihui Zhu

* 29 pages and 9 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold


Sep 19, 2022
Can Yaras, Peng Wang, Zhihui Zhu, Laura Balzano, Qing Qu

* The first two authors contributed to this work equally; 38 pages, 13 figures. Accepted at NeurIPS'22 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sparsity-guided Network Design for Frame Interpolation


Sep 09, 2022
Tianyu Ding, Luming Liang, Zhihui Zhu, Tianyi Chen, Ilya Zharkov

* Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence. The corresponding CVPR paper can be found at arXiv:2103.10559 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Error Analysis of Tensor-Train Cross Approximation


Jul 09, 2022
Zhen Qin, Alexander Lidiak, Zhexuan Gong, Gongguo Tang, Michael B. Wakin, Zhihui Zhu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features


Mar 12, 2022
Jinxin Zhou, Xiao Li, Tianyu Ding, Chong You, Qing Qu, Zhihui Zhu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Training under Label Noise by Over-parameterization


Feb 28, 2022
Sheng Liu, Zhihui Zhu, Qing Qu, Chong You

* 23 pages, 4 figures and 5 tables. Code is available at https://github.com/shengliu66/SOP 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery


Sep 23, 2021
Lijun Ding, Liwei Jiang, Yudong Chen, Qing Qu, Zhihui Zhu

* 75 pages, 3 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Only Train Once: A One-Shot Neural Network Training And Pruning Framework


Jul 15, 2021
Tianyi Chen, Bo Ji, Tianyu Ding, Biyi Fang, Guanyi Wang, Zhihui Zhu, Luming Liang, Yixin Shi, Sheng Yi, Xiao Tu

* Under Review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Geometric Analysis of Neural Collapse with Unconstrained Features


May 06, 2021
Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu

* 42 pages, 8 figures, 1 table; the first two authors contributed to this work equally 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>