Collaborative Research: CIF: Medium: Post-Modern Min-Max Optimization Theory: Departure from Classical Minimization Theory

NSF Award Search · 01002526DB NSF RESEARCH & RELATED ACTIVIT · $525,000 · view on nsf.gov ↗

Abstract

Min-max optimization underpins technologies ranging from generative Artificial Intelligence (AI) to large-scale reinforcement learning, yet today’s methods remain slow and unreliable for many real-world tasks. This suboptimality stems from the traditional approach of adapting minimization techniques to the min-max setup, which necessarily overlooks the unique complexities inherent in min-max problems. This project fundamentally revises this approach, developing specialized theoretical frameworks and efficient algorithms tailored explicitly to min-max optimization. By establishing a deeper understanding of these unique characteristics, the proposed research will significantly enhance the efficiency and robustness of min-max optimization, directly impacting practical applications in machine learning and artificial intelligence. Technically, this project will first explore core theoretical foundations under idealized convex-concave conditions, emphasizing accelerated convergence through anchor-type algorithms and enhanced stochastic methods with relaxed assumptions. Building upon this, the project will also develop practical algorithms that are robust to realistic, non-ideal conditions, including methods for nonconvex problems, efficient sampling strategies for stochastic settings, and adaptive update rules. Additionally, the research will investigate efficient alternating-update strategies, proximal gradient-type methods, and applications to training deep neural networks. T

Key facts

NSF award ID
2504626
Awardee
Johns Hopkins University (MD)
SAM.gov UEI
FTMTDMBR29C7
PI
Nicolas Loizou
Primary program
01002526DB NSF RESEARCH & RELATED ACTIVIT
All programs
Machine Learning Theory, COMM & INFORMATION FOUNDATIONS, MEDIUM PROJECT, SIGNAL PROCESSING
Estimated total
$525,000
Funds obligated
$525,000
Transaction type
Standard Grant
Period
08/15/2025 → 07/31/2028