This thrust focuses on applying optimization to speed up machine learning algorithms. Optimization algorithms, e.g., stochastic gradient algorithms, play a key role in training machine learning models. The thrust studies how to improve these algorithms, reduce their computational requirements, and capture important requirements with more fidelity. In particular, the thrust proposed novel optimization methods to impose sparsity in learning models, a fundamental feature for explainability. AI4OPT also devotes attention to learning models concerned with combinatorial objects. The thrust has shown that flow algorithms may be of significant benefits to a variety of learning tasks. 

Optimization for AI Team

Alper Atamturk
Alper Atamturk
Berkeley Site Director
University of California, Berkeley
Dorit Hochbaum
Dorit Hochbaum
University of California, Berkeley
George Lan
George Lan
Georgia Institute of Technology
Santanu Dey
Santanu Dey
Georgia Institute of Technology
Paul Grigas
Paul Grigas
University of California, Berkeley
Ramtin Madani
Ramtin Madani
UTA Site
University of Texas, Arlington
Renato Monteiro
Renato Monteiro
Georgia Institute of Technology
Arkadi Nemirovski
Arkadi Nemirovski
Georgia Institute of Technology
Haesun Park
Haesun Park
Georgia Institute of Technology
Justin Romberg
Justin Romberg
Deputy Director
Georgia Institute of Technology
Alexander Shapiro
Alexander Shapiro
Georgia Institute of Technology
Santosh Vempala
Santosh Vempala
Georgia Institute of Technology