Constantinos Daskalakis
Papers
1
Total Citations
8
H-Index
1
About
Constantinos Daskalakis is a pioneering computer scientist whose work bridges theoretical computer science, game theory, and machine learning. He is best known for his foundational contributions to the computational complexity of Nash equilibria, proving that finding a Nash equilibrium is PPAD-complete, a result that reshaped algorithmic game theory. His research also spans equilibrium computation, deep learning, and multi-agent reinforcement learning, where he explores how gradient-based methods can solve non-convex optimization problems in complex systems. With over 8,000 citations, his work has had a profound impact on both theory and practice, influencing fields from economics to artificial intelligence. Daskalakis has received numerous accolades, including the ACM Doctoral Dissertation Award, the Sloan Fellowship, and the Simons Investigator Award. His recent invited talk on "Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning" highlights his ongoing efforts to unify these areas, offering insights into how modern machine learning techniques can tackle longstanding challenges in game-theoretic equilibrium computation.
Research Focus
Key Achievements
Top Papers
- 1