Carl Hvarfner
Carl Hvarfner
A rather basic question, possibly related to previous issue by mfeurer regarding `n_retries`: Using the following setup (and latest pip version, 2.0.2): ``` initial_design = SobolInitialDesign(scenario, n_configs=10) intensifier = Intensifier(scenario,...
# 🐛 Bug With the risk of looking a bit silly, I don't think conditioning on additional observations works when using fully Bayesian GPs out of the box. ## To...
Hi, Thanks for a very good benchmarking suite! I scoured the training data briefly and could not find a instance where the number of layers were above 4. Is there...
A series of improvements directed towards improving the performance of PES & JES, as well as their MultiObj counterparts. This PR adds an initializer for the acquisition function optimization, which...
A series of improvements directed towards improving the performance of PES & JES, as well as their MultiObj counterparts. ## Motivation As pointed out by @SebastianAment in [this paper](https://arxiv.org/pdf/2310.20708), the...
Summary: Added 5 Feed benchmarks, three of which are constrained. The Benchmark construction: N7625716 Optimal values from 990 sobol + 10 BO: N7637108 Each benchmark is a MatheronPathModel (using Posterior...
Summary: This diff addresses two issues in the computation of inference trace: 1. The generation strategy is copied inside run_optimization_with_orchestrator --> we retrieve the traces on an unused generation strategy...