Optimization and Deep Learning



The Mines Optimization and Deep Learning (MODL) group conducts research in the intersection of deep learning and optimization. Current areas of interest include inverse problems, learning-to-optimize, applied probability, zeroth order optimization, and implicit deep learning. Our ongoing projects apply these techniques to problems from spatial statistics, optimal power flow, generative models, signal processing, and optimal control. For more information, feel free to contact any of the faculty listed below.

Optimization and Deep Learning Seminars

Optimization and Deep Learning meets on TBD.

Contact Dr. Samy Wu Fung or Dr. Daniel McKenzie if you are interested in attending.

Research Faculty 

Daniel McKenzie

email: dmckenzie@mines.edu

website: https://danielmckenzie.github.io/

  • Zeroth-order optimization and applications
  • Signal processing, particularly compressed sensing
  • Learning-to-optimize for inverse problems
  • Nonlinear dimensionality reduction
  • First passage percolation

Samy Wu Fung

email: swufung@mines.edu

website: https://swufung.github.io/

  • Inverse Problems, Optimization, Deep Learning
  • Optimal Control, Mean Field Games

Luis Tenorio

email: ltenorio@mines.edu

  • Statistical inverse problems
  • Applied probability
  • Experimental design


Amandin Chyba

Brandon Knutson

Katie Raitz

Jordan Pettyjohn

Antony Sikorski

Soraya Terrab