Movatterモバイル変換

Bayesian Optimization in PyTorch

Introduction Get started Tutorials

Key Features

Modular

Plug in new models, acquisition functions, and optimizers.

Built on PyTorch

Easily integrate neural network modules. Native GPU & autograd support.

Scalable

Support for scalable GPs via GPyTorch. Run code on multiple devices.

References

BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization

@inproceedings{balandat2020botorch,
  title = {{BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization}},
  author = {Balandat, Maximilian and Karrer, Brian and Jiang, Daniel R. and Daulton, Samuel and Letham, Benjamin and Wilson, Andrew Gordon and Bakshy, Eytan},
  booktitle = {Advances in Neural Information Processing Systems 33},
  year = 2020,
  url = {http://arxiv.org/abs/1910.06403}
}

Check out someother papers using BoTorch.

Get Started

Install BoTorch:
via pip (recommended):
```
pip install botorch
```
via Anaconda (from the unofficial conda-forge channel):
```
conda install botorch -c gpytorch -c conda-forge
```

Fit a model:

import torch
from botorch.modelsimport SingleTaskGP
from botorch.models.transformsimport Normalize, Standardize
from botorch.fitimport fit_gpytorch_mll
from gpytorch.mllsimport ExactMarginalLogLikelihood

train_X= torch.rand(10,2, dtype=torch.double)*2
Y=1- torch.linalg.norm(train_X-0.5, dim=-1, keepdim=True)
Y= Y+0.1* torch.randn_like(Y)# add some noise

gp= SingleTaskGP(
  train_X=train_X,
  train_Y=Y,
  input_transform=Normalize(d=2),
  outcome_transform=Standardize(m=1),
)
mll= ExactMarginalLogLikelihood(gp.likelihood, gp)
fit_gpytorch_mll(mll)

Construct an acquisition function:

from botorch.acquisitionimport LogExpectedImprovement

logEI= LogExpectedImprovement(model=gp, best_f=Y.max())

Optimize the acquisition function:

from botorch.optimimport optimize_acqf

bounds= torch.stack([torch.zeros(2), torch.ones(2)]).to(torch.double)
candidate, acq_value= optimize_acqf(
  logEI, bounds=bounds, q=1, num_restarts=5, raw_samples=20,
)
candidate# tensor([[0.2981, 0.2401]], dtype=torch.float64)