If you made any changes in Pure, your changes will be visible here soon.

Fingerprint Fingerprint is based on mining the text of the expert's scholarly documents to create an index of weighted terms, which defines the key subjects of each individual researcher.

  • 13 Similar Profiles
Base stations Engineering & Materials Science
Heterogeneous networks Engineering & Materials Science
Power control Engineering & Materials Science
Transceivers Engineering & Materials Science
Neural networks Engineering & Materials Science
Factorization Engineering & Materials Science
Neurons Engineering & Materials Science
Coordinate Descent Mathematics

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output 2011 2019

  • 9 Conference contribution
  • 9 Article
  • 2 Paper
  • 1 Conference article

On the convergence of a class of Adam-type algorithms for non-convex optimization

Chen, X., Liu, S., Sun, R. & Hong, M., Jan 1 2019.

Research output: Contribution to conferencePaper

Momentum
neural network
popularity
guarantee
learning

Worst-case complexity of cyclic coordinate descent: O(n2) gap with randomized version

Sun, R. & Ye, Y., Jan 1 2019, (Accepted/In press) In : Mathematical Programming.

Research output: Contribution to journalArticle

Coordinate Descent
Linear systems
Experiments
Projection onto Convex Sets
Gauss-Seidel Method

Adding one neuron can eliminate all bad local minima

Liang, S., Sun, R., Lee, J. D. & Srikant, R., Jan 1 2018, In : Advances in Neural Information Processing Systems. 2018-December, p. 4350-4360 11 p.

Research output: Contribution to journalConference article

Neurons
Neural networks

Understanding the loss surface of neural networks for binary classification

Liang, S., Sun, R., Li, Y. & Srikant, R., Jan 1 2018, 35th International Conference on Machine Learning, ICML 2018. Dy, J. & Krause, A. (eds.). International Machine Learning Society (IMLS), p. 4420-4429 10 p. (35th International Conference on Machine Learning, ICML 2018; vol. 6).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Neural networks
Hinges
Neurons

Understanding the loss surface of single-layered neural networks for binary classification

Liang, S., Sun, R., Srikant, R. & Li, Y., Jan 1 2018.

Research output: Contribution to conferencePaper

neural network
Neural networks
performance
Hinges
Neurons