I graduated with a PhD in Electrical and Computer Engineering from The University of Texas at Austin. My advisor was Constantine Caramanis. I obtained my B.E. from Tsinghua University in 2012. I have spent two summers as an intern at Google, where I made contributions to Google's recommendation and ads systems.
I am broadly interested in machine learning. My thesis research focused on developing tractable non-convex algorithms for modern data and learning problems with various constraints.
Email: yixy at utexas dot edu
Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization,
Xinyang Yi, Constantine Caramanis, Sujay Sanghavi.
Preprint, 2016. [arxiv]
Minimax Gaussian Classification and Clustering,
Tianyang Li, Xinyang Yi, Constantine Caramanis, Pradeep Ravikumar.
Artificial Intelligence and Statistics Conference (AISTATS), 2017.
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning,
Xinyang Yi*, Zhaoran Wang*, Zhuoran Yang*, Constantine Caramanis, Han Liu.
Neural Information Processing Systems Conference (NIPS), 2016. [nips link]
Optimal Linear Estimation under Unknown Nonlinear Transform,
Xinyang Yi, Zhaoran Wang, Constantine Caramanis, Han Liu.
Neural Information Processing Systems Conference (NIPS), 2015. [arxiv] [nips link]
Novel Power Grid Reduction Method Based on L1 Regularization,
Ye Wang, Meng Li, Xinyang Yi, Zhao Song, Constantine Caramanis and Micheal Orshansky.
Design Automation Conference (DAC), 2015. [pdf]