Georgios Piliouras
Google (United States)(US)Singapore University of Technology and Design(SG)Google DeepMind (United Kingdom)(GB)Google (United Kingdom)(GB)
Publications by Year
Research Areas
Game Theory and Applications, Advanced Bandit Algorithms Research, Evolutionary Game Theory and Cooperation, Reinforcement Learning in Robotics, Auction Theory and Applications
Most-Cited Works
- → First-order methods almost always avoid strict saddle points(2019)143 cited
- → Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile(2018)111 cited
- → Multiplicative Weights Update in Zero-Sum Games(2018)86 cited
- → Multiplicative updates outperform generic no-regret learning in congestion games(2009)83 cited
- → First-order Methods Almost Always Avoid Saddle Points(2017)76 cited
- → α-Rank: Multi-Agent Evaluation by Evolution(2019)71 cited
- → The Unusual Effectiveness of Averaging in GAN Training