Dohyun Kwon
Yonsei University · 情報科学
研究室紹介
Professor Dohyun Kwon's research lab specializes in the theoretical foundations of optimization dynamics, with a focus on continuous-time analysis of complex optimization problems. The lab develops unified frameworks for understanding time-scale separation in nested and hierarchical optimization, including minimax, bilevel, and min–min–max problems. By leveraging novel Lyapunov-based methods, the lab aims to establish modular, condition-agnostic analysis tools that bridge strong convexity to weaker error-bound conditions. The work emphasizes algorithmic design and convergence guarantees for modern machine learning and control systems.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
1We study single-loop gradient-flow dynamics for nested optimization, where the outer variable evolves while auxiliary variables track the inner solution map. While existing analyses typically rely on problem- and condition-specific Lyapunov constructions, we propose, to our knowledge, the first unified Lyapunov template for continuous-time analysis that covers minimax, bilevel via a lifted penalty formulation, and min--min--max. Our proof is modular, built from reusable lemmas that yield a unifi