Richard Y. Zhang

Assistant Professor
Department of Electrical and Computer Engineering
University of Illinois at Urbana-Champaign

I study optimization and machine learning, and their applications in power and energy systems. My goal is to use advanced computational capabilities to learn from large datasets and solve societal problems.

Contact - CV - Google Scholar - LinkedIn - StackExchange

Research

Power system optimization. Numerical algorithms for large-scale semidefinite programs. Nonconvex optimization. Machine learning for power applications.

News (Recent / All)

Videos (Recent / All)

How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?
NeurIPS 2018 Spotlight (5 min)
[paper] [slides] [poster]

Recommendation engines (think YouTube and Netflix) frequently make use of low-rank matrix models. In practice, these are easily trained using SGD, apparently without getting stuck at a local minimum. In this paper, we show that we've just been getting lucky—SGD is readily defeated by bad models that "look easy" to train.

Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
ICML 2018 (10 min)
[paper] [slides] [poster]

Graphical lasso is able to estimate a graphical model on \(n\) vertices from \(O(n\log(n))\) data points. We describe an algorithm that solves graphical lasso in linear \(O(n)\) time and memory, thereby allowing extremely large graphical models to be learned on laptop computers.

Publications (Select / All)

Preprints 2019 2018 2017 2016 2015 2014 2011-2013

Education & Training

Trivia

I am a New Zealander of Chinese descent from Christchurch, New Zealand. My last name 张/張 (Zhāng) is pronounced "Dj-uh-ng", but I usually go by the anglicized "Z-ang". 我会说普通话。J'ai étudié le français à l'école. I was a guitarist in the post-rock band Mammoth (see Two Weeks and Life without Light).

© 2018 Richard Y. Zhang.