Sebastian Ament

la_square.jpg

I am a PhD candidate in computer science at Cornell University, working with Carla Gomes. My research focus is on sparse and Bayesian optimization. On the applied side, I have collaborated with materials scientists in leveraging active learning for the discovery of novel meta-stable materials. After graduation, I will join Meta as a research scientist.

When I am not penciling Greek letters or hunting down missing minus signs in code, I enjoy cycling, dancing tango and playing the piano. Hear me play a tango that I transcribed here.

News

May 15, 2022 Our paper “Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation” got accepted to ICML 2022!
Jan 4, 2022 The Scientific Autonomous Reasoning Agent (video, paper) is featured in the Cornell Chronicle!

Selected Publications

  1. ICML
    Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation
    Ament, Sebastian, and Gomes, Carla
    In International Conference on Machine Learning 2022
  2. Sci. Adv.
    Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams
    Ament, Sebastian, Amsler, Maximilian, Sutherland, Duncan R., Chang, Ming-Chiang, Guevarra, Dan, Connolly, Aine B., Gregoire, John M., Thompson, Michael O., Gomes, Carla P., and Dover, R. Bruce
    Science Advances 2021
  3. ICML
    Sparse Bayesian Learning via Stepwise Regression
    Ament, Sebastian, and Gomes, Carla
    In International Conference on Machine Learning 2021