Gabriel P. Andrade
I'm an Applied Scientist at Amazon working on bad actor detection using machine learning. I received my PhD in computer science at the University of Colorado Boulder in the summer of 2022, where I was fortunate to be advised by Rafael Frongillo and Joshua Grochow. Before my PhD, I completed an MS in applied math at UMass Amherst.
Research Buzzwords:
Online Optimization, Algorithmic Economics, Game Theory, Dynamical Systems, Complex Networks, and Multi-Agent Learning
Publications:
- No-Regret Learning in Games is Turing Complete, G. P. Andrade, R. Frongillo, and G. Piliouras. (arXiv:2202.11871)
- Learning in Matrix Games Can Be Arbitrarily Complex, G. P. Andrade, R. Frongillo, and G. Piliouras. In Proceedings of the 34th Annual Conference on Learning Theory (COLT 2021)
- Graphical Economies with Resale, G. P. Andrade, R. Frongillo, E. Gorokhovsky, and S. Srinivasan. In Proceedings of the 21st ACM Conference on Economics and Computation (ACM EC 2021)
- Graph Models of Neurodynamics to Support Oscillatory Associative Memories, G. P. Andrade, M. Ruszinkó, and R. Kozma. In Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN 2018)
Articles and Manuscripts:
- Math Systems for Diagnosis and Treatment of Breast Cancer, C. Amorin, G. P. Andrade, S. Castro-Pearson, A. K. Geraldo, B. Iles, D. Katsaros, T. Mullen, S. Nguyen, O. Spiro, and M. Sych. In UMass Amherst Department of Mathematics & Statistics Newsletter (2017)
- A Matroid Generalization of Sperner's Lemma, G. P. Andrade, A. R. Rey, A. J. R. Sandoval, M. Sondjaja, and F. Su. (2015)