At ICML, Tiago da Silva Henrique and Daniel Csillag will present articles accepted after a rigorous selection process
ICML is one of the world's leading AI and machine learning events
From Rio de Janeiro to the research hub in Vienna, Austria, two students from the School of Applied Mathematics at Fundação Getulio Vargas (FGV EMAp) are ready to attend the 41st edition of the International Conference on Machine Learning (ICML). The event takes place from July 21 to 27 and is recognized as one of the world's leading academic conferences dedicated to artificial intelligence and machine learning. In addition to lectures and workshops, the conference includes a section dedicated to the exhibition and presentation of scientific papers.
Daniel Csillag and Tiago da Silva Henrique submitted their work to the rigorous double-blind review process carried out by the event organizers and will be among the researchers whose work reflects the most innovative and crucial advances in current research in artificial intelligence and machine learning. "This conference is internationally recognized, and having our work published there is an important achievement that demonstrates that we are competing globally with renowned researchers", says Tiago.
Daniel wrote the article together with Claudio José Struchiner and Guilherme Tegoni Goedert, professors at the School. The work entitled “Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis” provides theoretical guarantees for causal regressions.
“Our job is to assess and establish which of the existing algorithms can reliably and rigorously recover causal information, even under simple and applicable assumptions. In this way, we ensure that the predictions made by these algorithms reflect real causal relationships, rather than mere correlations”, explains Daniel.
Tiago graduated in Data Science from FGV EMAp | Photo: FGV EMAp
Tiago produced the paper “Embarrassingly Parallel GFlowNets” in partnership with Luiz Max Carvalho and Diego Mesquita, researchers at FGV EMAp, and Amauri Souza and Samuel Kaski, researchers at Aalto University, Finland. In the paper, they developed an algorithm to perform parallel Bayesian inference on distributions over a finite number of variables.
Young researchers in the spotlight
Tiago's career has been marked by educational excellence since he lived in Florianópolis and attended elementary school in a public school. After performing remarkably well in the Brazilian Mathematics Olympiad for Public Schools (OBMEP), he decided to pursue higher education at FGV EMAp, where he found a pioneering course that combined computing, mathematics and data analysis. "I was captivated not only by the program's innovation, but also by the opportunity to have classes with a distinguished team of professors", he says.
Currently studying for a master's degree, Tiago is also enrolled in doctoral courses, which, in his view, has provided a solid foundation for conducting high-quality research. "One of the most valuable aspects of FGV EMAp is having this opportunity to access postgraduate courses during undergraduate studies", he emphasizes.
Daniel marcará presença na Áustria representando a FGV EMAp | Foto: FGV EMAp
O paulista Daniel ressalta que a Escola promove ativamente o contato entre seus alunos e pesquisas de ponta de todo o mundo. "A FGV EMAp oferece um ambiente ótimo para colaborações e produções acadêmicas de alta qualidade. Eventos como esse proporcionam uma excelente oportunidade para a publicação e divulgação do nosso trabalho", completa.