Qiang Liu

me 

Qiang Liu
Associate Professor
Computer Science
University of Texas at Austin
lqiang@cs.utexas.edu (for UT business)
qiang.liu.research@gmail.com
Office: GDC 4.806
Phone: 512-232-7866

("Qiang" sounds like "Chee-ah-ng", and "Liu" as "l-yo")

Research

I aim to develop useful algorithms, by simplifying complexity and uncovering mathematical essence. I am broadly interested in the algorithmic core of machine learning, wherever mathematical insights can unlock new capabilities.

<My Google scholar>

Selected Works

  • Lion-K is a principled generalization of the machine-discovered Lion optimization program, with convergence verified via a Lyapunov function [Lion-K, slides]. [New] Lion-K also captures the more recent Muon optimizer, which solves optimization problems under spectral norm constraints. See blog post.

  • Steepest Descent Methods for Neural Architecture Optimization: Going Beyond Black Boxes

  • Distributed Learning, Information Loss and Curved Exponential Families [paper, slides]

  • Variational Inference for Crowdsourcing [paper, slides]

Working with me

If you are a UT student interested in working with me, please consider enrolling in one of my classes and interacting with me there.

If you are applying for graduate studies at UT and wish to work with me, please indicate your interest in your application and research statement. Please do NOT email me directly.

Teaching

  • Undergraduate intro to machine learning [here].

  • Undergraduate intro to optimization [here]

  • Lecture notes on probabilistic learning and inference [here]

  • Learning theory (graduate level, scribed notes, not proofreaded!) [here]

  • Advanced ML for undergraduates (scribed notes, not proofreaded!) [here]