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.

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, generative modeling, and aggregation for collective decision making, primarily under differential privacy constraints.

Previously, I obtained my MSc in Engineering from the Institute for Mathematical and Computational Engineering at the Catholic University of Chile, where I was advised by Cristobal Guzman. I was also a Student Researcher at Google DeepMind working with Courtney Paquette and Fabian Pedregosa.

Research

Preprints

• Sequentially Auditing Differential Privacy
  Tomas Gonzalez, Mateo Dulce-Rubio, Aaditya Ramdas, Monica Ribero
  Submitted
  
• Private Evolution Converges
  Tomas Gonzalez, Giulia Fanti, Aaditya Ramdas
  Submitted
  

Publications

• Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
  Tomas Gonzalez, Cristobal Guzman, Courtney Paquette
  COLT 2024
  
• 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