Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Brownian Bandits
Published in , 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Barış Ata, J. Michael Harrison, Dawei Li. "Brownian Bandits
NTK-SAP: Improving Neural Network Pruning by Aligning Training Dynamics
Published in International Conference on Learning Representation, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Yite Wang, Dawei Li, Ruoyu Sun. (2023). "NTK-SAP: Improving Neural Network Pruning by Aligning Training Dynamics. " International Conference on Learning Representation. 2023.
On a Faster R-Linear Convergence Rate of the Barzilai-Borwein Method
Published in Preprint, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Dawei Li, Ruoyu Sun. (2021). "On a Faster R-Linear Convergence Rate of the Barzilai-Borwein Method. " Preprint.. 2021.
On the Benefit of Width for Neural Networks: Disappearance of Basins
Published in SIAM Journal on Optimization, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Dawei Li, Tian Ding, and Ruoyu Sun. (2022). "On the benefit of width for neural networks: Disappearance of basins." SIAM Journal on Optimization. 32.3 (2022): 1728-1758.
RMSprop Converges with Proper Hyper-Parameter
Published in International Conference on Learning Representation, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Naichen Shi, Dawei Li, Mingyi Hong, Ruoyu Sun. (2021). "RMSprop Converges with Proper Hyper-Parameter. " International Conference on Learning Representation. 2021.
Suboptimal Local Minima Exist for Wide Neural Networks with Smooth Activations
Published in Mathematics of Operations Research, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Tian Ding, Dawei Li, and Ruoyu Sun. (2022). "Suboptimal Local Minima Exist for Wide Neural Networks with Smooth Activations." Mathematics of Operations Research. 47.4 (2022): 2784-2814.
The Global Landscape of Neural Networks: An Overview.
Published in IEEE Signal Processing Magazine, 1900
The contents above will be part of a list of publications, if the user clicks the link for the publication than the contents of section will be rendered as a full page, allowing you to provide more information about the paper for the reader. When publications are displayed as a single page, the contents of the above “citation” field will automatically be included below this section in a smaller font.
Recommended citation: Ruoyu Sun, Dawei Li, Shiyu Liang, Tian Ding and Rayadurgam Srikant. (2020). "The Global Landscape of Neural Networks: An Overview. " IEEE Signal Processing Magazine. 37.5 (2020): 95-108.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching
, , 1900