Profile

I am a research scientist at Google working on differential privacy. Before that I completed my Ph.D. in Electrical and Computer Engineering at UT Austin, advised by Prof. Haris Vikalo. I was (am) interested in enabling private machine learning systems so my research focused on addressing resource constraints in federated learning and improving the utility of differentially private algorithms. Before that I was lucky to study math at Universidad de Los Andes in my hometown Bogotá, Colombia, and to be advised by Prof. Mauricio Velasco.

Papers

In alphabetical order.

Easy Differentially Private Linear Regression. ICLR 2023. With Kareem Amin, Matthew Joseph, and Sergei Vassilvitskii
Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints. IEEE JSTSP 2023. With Gustavo De Veciana and Haris Vikalo.
A Joint Exponential Mechanism for Differentially Private Top-k. ICML 2022. With Jennifer Gillenwater, Matthew Joseph, and Andrés Muñoz Medina.
Federating recommendations using differentially private prototypes. Pattern Recognition 2022. With Jette Henderson, Haris Vikalo, and Sinead Williamson.
(Nearly) Dimension Independent Private ERM with AdaGrad Rates{via Publicly Estimated Subspaces. COLT 2021. With Peter Kairouz, Keith Rush, and Abhradeep Thakurta.

Other

I enjoy movement (climbing, yoga, swimming, biking), reading fiction (Annie Dillard’s short stories or Juan Gabriel Vasquez novels), and try my best to stay connected with the machine learning community in Colombia and South America.

Experience

I completed my B.S. in Mathematics from Universidad de Los Andes in 2015 in Colombia. I worked on Monte Carlo methods for hypothesis testing on contingency tables under the supervision of Prof. Mauricio Velasco. Afterwards, I had the chance to work with Google LA through the Research for industrial Problems for Students program at UCLA, and later as a data science researcher for industry and government projects at Quantil.

I was a TA for Linear Algebra and Integral Calculus at Universidad de Los Andes. During my PhD at UT Austin, I had the opportunity to intern at Bell Labs, CognitiveScale, and Google. I was also a TA for the Data Science Lab undergraduate course, and for the convex optimization graduate course.