Cristóbal Guzmán

works on

differential privacy 1 fixed-parameter tractability 1 linear programming 1 multiplicative weights 1 synthetic data 1 treewidth 1

From the 1 of 12 linked papers with an AI index.

activity

20242026

most citedHow to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

1 citations · 1 across the 5 of their papers we have counts for

collaborators

Showing math.OCShow all

3 papers · 1 filter

math.OC2025

Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems

TomÃ¡s GonzÃ¡lez, CristÃ³bal GuzmÃ¡n, Courtney Paquette

We study the problem of differentially-private (DP) stochastic (convex-concave) saddle-points in the $ℓ_{1}$ setting. We propose $(ε, I^´)$ -DP algorithms based on stochas…

math.OC2025

Non-Euclidean High-Order Smooth Convex Optimization

Juan Pablo Contreras, CristÃ³bal GuzmÃ¡n, David MartÃnez-Rubio

We develop algorithms for the optimization of convex objectives that have HÃ¶lder continuous $q$ -th derivatives by using a $q$ -th order oracle, for any $q \geq 1$ . Our algorithms w…

math.OC2024

Optimization on a Finer Scale: Bounded Local Subgradient Variation Perspective

Jelena Diakonikolas, CristÃ³bal GuzmÃ¡n

We initiate the study of nonsmooth optimization problems under bounded local subgradient variation, which postulates bounded difference between (sub)gradients in small local region…