Paul Brunzema
@pbrunzema.bsky.social
PhD student on learning-based control; interested in everything around Bayesian optimization and robotics
Beautiful Vancouver—enjoying some days off after an inspiring yet exhausting NeurIPS 2024. With 16,500 attendees, countless technical discussions, and a few nice beers on the side, it’s been a great experience!
December 17, 2024 at 10:27 PM
Beautiful Vancouver—enjoying some days off after an inspiring yet exhausting NeurIPS 2024. With 16,500 attendees, countless technical discussions, and a few nice beers on the side, it’s been a great experience!
Our results show our approach of VBLLs + MLP features + our training approach yields SOTA or near-SOTA performance on a bunch of problems from classic 2D Ackley, all the way to much more challenging problems with discrete inputs and controller tuning.
December 14, 2024 at 8:59 PM
Our results show our approach of VBLLs + MLP features + our training approach yields SOTA or near-SOTA performance on a bunch of problems from classic 2D Ackley, all the way to much more challenging problems with discrete inputs and controller tuning.
To accelerate training, we combine model optimization with last-layer conditioning. This is a useful bridge between efficient Bayesian conditioning and NN optimization and massively accelerates training at (almost) no performance cost (see black vs purple or green curve in the figure).
December 14, 2024 at 8:59 PM
To accelerate training, we combine model optimization with last-layer conditioning. This is a useful bridge between efficient Bayesian conditioning and NN optimization and massively accelerates training at (almost) no performance cost (see black vs purple or green curve in the figure).
📚 New Paper with collaborators from DTU, Vector, & Google DeepMind
A neural net-based approach to BO that performs well in both classic, small-scale problems, and can efficiently scale far beyond GP surrogate models.
Visit our poster @ NeurIPS Bayesian decision-making workshop today!
More info👇
A neural net-based approach to BO that performs well in both classic, small-scale problems, and can efficiently scale far beyond GP surrogate models.
Visit our poster @ NeurIPS Bayesian decision-making workshop today!
More info👇
December 14, 2024 at 8:59 PM
📚 New Paper with collaborators from DTU, Vector, & Google DeepMind
A neural net-based approach to BO that performs well in both classic, small-scale problems, and can efficiently scale far beyond GP surrogate models.
Visit our poster @ NeurIPS Bayesian decision-making workshop today!
More info👇
A neural net-based approach to BO that performs well in both classic, small-scale problems, and can efficiently scale far beyond GP surrogate models.
Visit our poster @ NeurIPS Bayesian decision-making workshop today!
More info👇