Mario Bravo
Mario Bravo
El académico Mario Bravo es Ph.D. en Matemáticas Aplicadas de la Universidad Pierre et Marie Curie, en Francia; Magíster en Matemáticas Aplicadas de la misma casa de estudios e ingeniero civil matemático con Magíster en Transporte, de la Universidad de Chile.
Su investigación se centra en la teoría de juegos en matemáticas aplicadas, algoritmos de aproximación estocástica, aplicaciones a optimización, entre otros. Se incorporó a la Facultad de Ingeniería y Ciencias de la Universidad Adolfo Ibáñez en 2021.
Anteriormente, el profesor Bravo se desempeñó como profesor en la Universidad de Santiago de Chile. Mario Bravo se ha adjudicado varios proyectos Fondecyt y becas CONICYT, junto con una beca entregada por el gobierno de Francia para realizar estudios de doctorado.
Stochastic Halpern iteration in normed spaces and applications to reinforcement learning</>
Bravo, M. & Contreras, J., 2026, In: Mathematical Programming.Mixing Times and Privacy Analysis for the Projected Langevin Algorithm under a Modulus of Continuity</>
Bravo, M., Flores-Mella, J. & Guzmán, C., 2025, In: Journal of Machine Learning Research, 26.Near-Optimal Sample Complexity for MDPs via Anchoring</>
Lee, J., Bravo, M. & Cominetti, R., 2025, In: Proceedings of Machine Learning Research, 267, p. 32907-32929.STOCHASTIC FIXED-POINT ITERATIONS FOR NONEXPANSIVE MAPS</>
Bravo, M. & Cominetti, R., 2024, In: SIAM Journal on Control and Optimization, 62, 1, p. 191-219.UNIVERSAL BOUNDS FOR FIXED POINT ITERATIONS VIA OPTIMAL TRANSPORT METRICS</>
Bravo, M., Champion, T. & Cominetti, R., dic. 2022, In: Applied Set-Valued Analysis and Optimization, 4, 3, p. 293-310.Learning with minimal information in continuous games</>
Bervoets, S., Bravo, M. & Faure, M., nov. 2020, In: Theoretical Economics, 15, 4, p. 1471-1508.Rates of convergence for inexact Krasnosel’skii–Mann iterations in Banach spaces</>
Bravo, M., Cominetti, R. & Pavez-Signé, M., may. 2019, In: Mathematical Programming, 175, 1-2, p. 241-262.Sharp convergence rates for averaged nonexpansive maps</>
Bravo, M. & Cominetti, R., ago. 2018, In: Israel Journal of Mathematics, 227, 1, p. 163-188.Bandit learning in concave n-person games</>
Bravo, M., Leslie, D. & Mertikopoulos, P., 2018, In: Advances in Neural Information Processing Systems, 2018-December, p. 5661-5671.On the robustness of learning in games with stochastically perturbed payoff observations</>
Bravo, M. & Mertikopoulos, P., may. 2017, In: Games and Economic Behavior, 103, p. 41-66.An adjusted payoff-based procedure for normal form games</>
Bravo, M., nov. 2016, In: Mathematics of Operations Research, 41, 4, p. 1469-1483.Reinforcement learning with restrictions on the action set</>
Bravo, M. & Faure, M., 2015, In: SIAM Journal on Control and Optimization, 53, 1, p. 287-312.An integrated behavioral model of the land-use and transport systems with network congestion and location externalities</>
Bravo, M., Briceño, L., Cominetti, R., Cortés, C. & Martínez, F., may. 2010, In: Transportation Research Part B: Methodological, 44, 4, p. 584-596.Convergence and nonconvergence in discrete-time stochastic iterations</>
Bravo, M. (Principal Investigator)1/04/19 → 1/04/24.
Dynamics and learning with partial interactions</>
Bravo, M. (Principal Investigator)15/11/15 → 15/11/18.
Adaptive procedures in games and population dynamics: methods and applications </>
Bravo, M. (Principal Investigator)1/03/12 → 1/03/15.
Information and Computation in Market Design</>
Bravo, M. (Principal Investigator)1/12/21 → 1/12/24.
Stochastic Fixed Point Iterations and Reinforcement Learning</>
Cominetti, R. (Principal Investigator) & Bravo, M. (Co-Investigator)1/04/24 → 1/04/28.