St. Louis County
Automating Bayesian optimization with Bayesian optimization
Gustavo Malkomes, Roman Garnett
Global optimization of expensive, potentially gradient-free functions has long been a critical component of many complex problems in science and engineering.
Exact Verification of ReLU Neural Control Barrier Functions
In CBF-based control, the desired safety properties of the system are mapped to nonnegativity of a CBF, and the control input is chosen to ensure that the CBF remains nonnegative for all time.
Replicability in Learning: Geometric Partitions and Sperner-KKM Lemma
Recent works have revealed the role of geometric partitions and Sperner's
Cost Effective Active Search
Shali Jiang, Roman Garnett, Benjamin Moseley
Neural Information Processing Systems http://nips.cc/
Training Image Estimators without Image Ground Truth
Neural Information Processing Systems http://nips.cc/
Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
Recently, various strategies for distributed training of large language models (LLMs) have been proposed.
Neural Lyapunov Control for Discrete-Time Systems
However, finding Lyapunov functions for general nonlinear systems is a challenging task.