Daniel Csillag

Profile

I'm an applied mathematician working on machine learning, statistics and compilers.
Currently doing research at FGV EMAp.

My research focuses on the methodology and theory of machine learning and statistics, with a flair of nonparametrics. I also do applications, usually in the form of collaborations.

Publications

Image Super-Resolution with Guarantees via Conformal Generative Models

Image Super-Resolution with Guarantees via Conformal Generative Models

Eduardo Adame, Daniel Csillag, G. Goedert

ArXiv

ABSHTMLPDF
Prediction-Powered E-Values

Prediction-Powered E-Values

Daniel Csillag, C. Struchiner, G. Goedert

ArXiv

ABSHTMLPDF

The impact of vaccination on the length of stay of hospitalized COVID-19 patients in Brazil.

Cleber Vinicius Brito dos Santos, Lara Esteves Coelho, Tatiana Guimarães de Noronha, G. Goedert, Daniel Csillag, Paula M Luz, Guilherme Loureiro Werneck, Daniel Antunes Maciel Villela, C. Struchiner

Vaccine 2025

ABS
Strategic Conformal Prediction

Strategic Conformal Prediction

Daniel Csillag, C. Struchiner, G. Goedert

AISTATS 2025

ABSHTMLPDF
SARS-CoV-2 transmission in a highly vulnerable population of Brazil: a household cohort study

SARS-CoV-2 transmission in a highly vulnerable population of Brazil: a household cohort study

L. Coelho, P. Luz, D. C. Pires, E. Jalil, Hugo Perazzo, Thiago S. Torres, Sandra W. Cardoso, E. Peixoto, S. Nazer, Eduardo Massad, Luiz Max Carvalho, W. Réquia, F. Motta, M. Siqueira, Ana Tereza Ribeiro de Vasconcelos, G. C. da Fonseca, Liliane T.F. Cavalcante, C. A. Costa, R. Amancio, Daniel A.M. Villela, Tiago Pereira, G. Goedert, C. V. Santos, Nadia C.P. Rodrigues, Breno Augusto Bormann de Souza Filho, Daniel Csillag, B. Grinsztejn, V. Veloso, C. Struchiner

The Lancet Regional Health - Americas 2024

ABS
Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis

Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis

Daniel Csillag, C. Struchiner, G. Goedert

ICML 2024

ABSHTMLPDF
AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification

AmnioML: Amniotic Fluid Segmentation and Volume Prediction with Uncertainty Quantification

Daniel Csillag, Lucas Monteiro Paes, Thiago Ramos, J. V. Romano, R. Schuller, Roberto B. Seixas, Roberto I Oliveira, Paulo Orenstein

AAAI Conference on Artificial Intelligence 2023 (IAAI)

ABSPDF
ExactBoost: Directly Boosting the Margin in Combinatorial and Non-decomposable Metrics

ExactBoost: Directly Boosting the Margin in Combinatorial and Non-decomposable Metrics

Daniel Csillag, C. Piazza, Thiago Ramos, J. V. Romano, R. I. Oliveira, Paulo Orenstein

AISTATS 2022

Optimizing Combinatorial and Non-decomposable Metrics with ExactBoost

Optimizing Combinatorial and Non-decomposable Metrics with ExactBoost

Daniel Csillag, C. Piazza, Thiago Ramos, J. V. Romano, Roberto I Oliveira, Paulo Orenstein