Cristóbal Guzmán — accepted AI-conference papers

2021

The complexity of nonconvex-strongly-concave minimax optimization

Siqi Zhang, Junchi Yang, Cristóbal Guzmán, Negar Kiyavash, Niao He

UAI 2021poster

This paper studies the complexity for finding approximate stationary points of nonconvex-strongly-concave (NC-SC) smooth minimax problems, in both general and averaged smooth finite-sum settings. We establish nontrivial lower complexity bounds for the two settings, respectively. Our result reveals s…

Cited by 85 Source ↗PDF ↗Scholar ↗

2020

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, Kunal Talwar

NeurIPS 2020spotlight

Uniform stability is a notion of algorithmic stability that bounds the worst case change in the model output by the algorithm when a single data point in the dataset is replaced. An influential work of Hardt et al. [2016] provides strong upper bounds on the uniform stability of the stochastic gradie…

Cited by 223 Source ↗PDF ↗Scholar ↗