Search for: All records

Creators/Authors contains: "Yin, W"

« Prev Next »

Total Resources

4

Resource Type
Conference Paper

2

Conference Proceeding

0

Dataset

0

Journal Article

2

Workshop Report

0

Availability
Full Text / Resource Available

4

Citation Only

0

Save Results
Excel (limit 2000)
CSV (limit 5000)
XML (limit 5000)

Have feedback or suggestions for a way to improve these results?
!

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

A Single-Timescale Method for Stochastic Bilevel Optimization

Chen, T. ; Sun, Y. ; Xiao, Q. ; Yin, W. ( March 2022 , International Conference on Artificial Intelligence and Statistics)

Full Text Available
Emergence of Spinons in Layered Trimer Iridate Ba4Ir3O10

https://doi.org/10.1103/PhysRevLett.129.207201

Shen, Y. ; Sears, J. ; Fabbris, G. ; Weichselbaum, A. ; Yin, W. ; Zhao, H. ; Mazzone, D. G. ; Miao, H. ; Upton, M. H. ; Casa, D. ; et al ( November 2022 , Physical Review Letters)

Full Text Available
Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Xia, C ; Yin, W ; Feng, Y ; Yu, P. S. ( April 2021 , NAACL-HLT)
null (Ed.)
Full Text Available
A parallel method for earth mover’s distance

Gangbo, W. ; Li, W. ; Osher, S. ; Ryu, E. ; Yin, W. ( January 2018 , Journal of scientific computing)

We propose a new algorithm to approximate the Earth Mover's distance (EMD). Our main idea is motivated by the theory of optimal transport, in which EMD can be reformulated as a familiar L1 type minimization. We use a regularization which gives us a unique solution for this L1 type problem. The new regularized minimization is very similar to problems which have been solved in the fields of compressed sensing and image processing, where several fast methods are available. In this paper, we adopt a primal-dual algorithm designed there, which uses very simple updates at each iteration and is shown to converge very rapidly. Several numerical examples are provided.
more » « less
Full Text Available