I’m a PhD student in the Machine Learning Department at Carnegie Mellon University, co-advised by Aaditya Ramdas and Giulia Fanti, and a member of the StatML group. My research is generously supported by the JP Morgan Chase AI PhD Fellowship.
I’m broadly interested in the algorithmic and statistical aspects of modern machine learning. I work on problems that I find both practically relevant and intellectually challenging, with research spanning areas such as optimization and generative modeling, primarily under differential privacy constraints.
Previously, I obtained my MSc from the Institute for Mathematical and Computational Engineering at the Catholic University of Chile, advised by Cristobal Guzman. I was also a Student Researcher at Google working with Courtney Paquette and Fabian Pedregosa.
Research
Preprints
- Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity
Diego Martinez-Taboada, Tomas Gonzalez, Aaditya Ramdas
Publications
- Private Evolution Converges
Tomas Gonzalez, Giulia Fanti, Aaditya Ramdas
NeurIPS 2025 - Sequentially Auditing Differential Privacy
Tomas Gonzalez, Mateo Dulce-Rubio, Aaditya Ramdas, Monica Ribero
NeurIPS 2025 - Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
Tomas Gonzalez, Cristobal Guzman, Courtney Paquette
SIAM Journal on Optimization 2025 (To appear)
COLT 2024 (Extended abstract) - Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
Raman Arora, Raef Bassily, Tomas Gonzalez, Cristobal Guzman, Michael Menart, Enayat Ullah
ICML 2023