Google Research

Black-Box Optimization of Unimodal Functions

UAI 2023 (2023)


We provide an intuitive new algorithm for black-box stochastic optimization of unimodal functions, a function class that we observe empirically can capture hyperparameter-tuning loss surfaces. Our method's convergence guarantee automatically adapts to Lipschitz constants and other problem difficulty parameters, recovering and extending prior results. We complement our theoretical development with experimentally validation on hyperparameter tuning tasks.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work