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

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

Sampling Engineering & Materials Science
Recovery Engineering & Materials Science
Channel capacity Engineering & Materials Science
Compressed sensing Engineering & Materials Science
Random Systems Mathematics
Quadratic Systems Mathematics
Convex optimization Engineering & Materials Science
Covariance matrix Engineering & Materials Science

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

Research Output 2010 2019

  • 546 Citations
  • 11 h-Index
  • 21 Conference contribution
  • 16 Article
  • 1 Conference article

Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval

Chen, Y., Chi, Y., Fan, J. & Ma, C., Jul 1 2019, In : Mathematical Programming. 176, 1-2, p. 5-37 33 p.

Princeton University

Research output: Contribution to journalArticle

Phase Retrieval
Gradient Descent
Initialization
Global Convergence
Learning systems

The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square

Sur, P., Chen, Y. & Candès, E. J., Jan 1 2019, (Accepted/In press) In : Probability Theory and Related Fields.

Princeton University

Research output: Contribution to journalArticle

Chi-square
Likelihood Ratio Test
Logistic Regression
Log-likelihood Ratio
Wilks' Theorem

Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval and matrix completion

Ma, C., Wang, K., Chi, Y. & Chen, Y., Jan 1 2018, 35th International Conference on Machine Learning, ICML 2018. Dy, J. & Krause, A. (eds.). International Machine Learning Society (IMLS), Vol. 8. p. 5264-5331 68 p.

Princeton University

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

Trimming
Trajectories
Sampling
Geometry
Costs
3 Citations (Scopus)

The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences

Chen, Y. & Candès, E. J., Aug 1 2018, In : Communications on Pure and Applied Mathematics. 71, 8, p. 1648-1714 67 p.

Princeton University

Research output: Contribution to journalArticle

Power Method
Maximum likelihood
Labels
Pairwise
Alignment
3 Citations (Scopus)

On the Minimax Capacity Loss under Sub-Nyquist Universal Sampling

Chen, Y., Goldsmith, A. J. & Eldar, Y. C., Jun 1 2017, In : IEEE Transactions on Information Theory. 63, 6, p. 3348-3367 20 p., 7903620.

Princeton University

Research output: Contribution to journalArticle

Sampling
Bandwidth
Low pass filters
Modulation
recipient