botorch
botorch copied to clipboard
pytorch
Bayesian optimization in PyTorch
# 🐛 Bug When I am conducting actual chemical experiments, I take the solvent ratio as the input of my multi-objective Bayesian optimization, and use optimize_ acqf_ This function is...
Summary: Introduces `utils/probability` submodule with the following offers: - `bvn`: Methods for computing bivariate normal probabilities and moments. - `MVNXPB`: Approximate solver for Multivariate Normal CDF. - `LinearEllipticalSliceSampler`: Class for...
Summary: Due to [this linear operator PR](https://github.com/cornellius-gp/linear_operator/pull/14), we should now be able to remove the custom logic in `Standardize` without performance impact. Differential Revision: D39746709
I am using HeteroskedasticSingleTaskGP model and qNEI acquisition function to optimise some parameters in a Navier Stokes equations solver. For a certain simulation case I can run the solver and...
Summary: Unfortunately, scipy does not allow timing out the optimization based on wall time. This diff implements a lightweight wrapper around `scipy.optimize.minimize` to achieve this. The new `minimize_with_timeout` method calls...
If you are submitting a bug report or feature request, please use the respective issue template. ## Issue description The [newest release](https://github.com/cornellius-gp/gpytorch/blame/master/gpytorch/utils/broadcasting.py) of gypytorch deprecated gpytorch.utils.broadcasting causing an import error...
Summary: This diff presents a minimal implementation of input transforms in GPyTorch. See cornellius-gp/gpytorch#2114 for GPyTorch side of these changes. What this does: * Moves the `transform_inputs` from BoTorch `Model`...
## Issue description I'm evaluating the performance of NEI vs EI on two in silico bioprocess models. When there is no noise on the observations, EI clearly outperforms a random...
# 🐛 Bug optimize_acqf should return a tensor with shape q when sequential = False and return_best_only = True however it returns an a single value. Following the code down...
# 🚀 Feature Request Currently `botorch` implements the `UpperConfidenceBound` analytic and MC acquisition functions in e.g. `botorch.acquisition.UpperConfidenceBound`. This is useful but it might be nice to have a pure "active...
